Spaces:
Runtime error
Runtime error
Yotam-Perlitz
commited on
Commit
·
ad12749
1
Parent(s):
f7f5843
clear cache
Browse filesSigned-off-by: Yotam-Perlitz <y.perlitz@ibm.com>
- assets/combined_20240704.csv +0 -0
- assets/combined_holistic_20240708.csv +0 -938
- cache/agreements_cache_42471fdfe00c7ff9b0aba18b66ab5a5f.csv +0 -73
- cache/agreements_cache_6ac32881b7d0a3bf6d8762ff242ff449.csv +0 -721
- cache/agreements_cache_9aca1000dd25da3a044f5fd80fad0266.csv +0 -721
- cache/agreements_cache_a8b645e4d5ba862fbfa9ef3ecf73b44c.csv +0 -721
- cache/agreements_cache_facdc1028ee0edd9aed491afc51b884d.csv +0 -73
assets/combined_20240704.csv
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
assets/combined_holistic_20240708.csv
DELETED
|
@@ -1,938 +0,0 @@
|
|
| 1 |
-
model,score,scenario,source,aggragated_from
|
| 2 |
-
gpt_4_turbo_2024_04_09,82.6,arena_hard,arena_hard_2404,[]
|
| 3 |
-
gpt_4_0125_preview,78.0,arena_hard,arena_hard_2404,[]
|
| 4 |
-
gemini_1.5_pro_api_preview,72.0,arena_hard,arena_hard_2404,[]
|
| 5 |
-
yi_large,63.7,arena_hard,arena_hard_2404,[]
|
| 6 |
-
claude_3_opus_20240229,60.4,arena_hard,arena_hard_2404,[]
|
| 7 |
-
glm_4,55.7,arena_hard,arena_hard_2404,[]
|
| 8 |
-
gpt_4_0314,50.0,arena_hard,arena_hard_2404,[]
|
| 9 |
-
gemini_1.5_flash_api_preview,49.6,arena_hard,arena_hard_2404,[]
|
| 10 |
-
claude_3_sonnet_20240229,46.8,arena_hard,arena_hard_2404,[]
|
| 11 |
-
claude_3_haiku_20240307,41.5,arena_hard,arena_hard_2404,[]
|
| 12 |
-
llama_3_70b_chat,41.1,arena_hard,arena_hard_2404,[]
|
| 13 |
-
gpt_4_0613,37.9,arena_hard,arena_hard_2404,[]
|
| 14 |
-
mistral_large_2402,37.7,arena_hard,arena_hard_2404,[]
|
| 15 |
-
mixtral_8x22b_instruct_v0.1,36.4,arena_hard,arena_hard_2404,[]
|
| 16 |
-
qwen1.5_72b_chat,36.1,arena_hard,arena_hard_2404,[]
|
| 17 |
-
command_r_plus,33.1,arena_hard,arena_hard_2404,[]
|
| 18 |
-
mistral_medium,31.9,arena_hard,arena_hard_2404,[]
|
| 19 |
-
mistral_next,27.4,arena_hard,arena_hard_2404,[]
|
| 20 |
-
gpt_3.5_turbo_0613,24.8,arena_hard,arena_hard_2404,[]
|
| 21 |
-
claude_2.0,24.0,arena_hard,arena_hard_2404,[]
|
| 22 |
-
dbrx_instructruct,23.9,arena_hard,arena_hard_2404,[]
|
| 23 |
-
mixtral_8x7b_instruct_v0.1,23.4,arena_hard,arena_hard_2404,[]
|
| 24 |
-
gpt_3.5_turbo_0125,23.3,arena_hard,arena_hard_2404,[]
|
| 25 |
-
yi_34b_chat,23.1,arena_hard,arena_hard_2404,[]
|
| 26 |
-
starling_lm_7b_beta,23.0,arena_hard,arena_hard_2404,[]
|
| 27 |
-
claude_2.1,22.8,arena_hard,arena_hard_2404,[]
|
| 28 |
-
snorkel_mistral_pairrm_dpo,20.7,arena_hard,arena_hard_2404,[]
|
| 29 |
-
llama_3_8b_chat,20.6,arena_hard,arena_hard_2404,[]
|
| 30 |
-
gpt_3.5_turbo_1106,18.9,arena_hard,arena_hard_2404,[]
|
| 31 |
-
gpt_3.5_turbo_0301,18.1,arena_hard,arena_hard_2404,[]
|
| 32 |
-
gemini_1.0_pro,17.8,arena_hard,arena_hard_2404,[]
|
| 33 |
-
snowflake_arctic_instruct,17.6,arena_hard,arena_hard_2404,[]
|
| 34 |
-
command_r,17.0,arena_hard,arena_hard_2404,[]
|
| 35 |
-
phi_3_mini_128k_instruct,15.4,arena_hard,arena_hard_2404,[]
|
| 36 |
-
tulu_2_dpo_70b,15.0,arena_hard,arena_hard_2404,[]
|
| 37 |
-
starling_lm_7b_alpha,12.8,arena_hard,arena_hard_2404,[]
|
| 38 |
-
mistral_7b_instruct,12.6,arena_hard,arena_hard_2404,[]
|
| 39 |
-
gemma_1.1_7b_it,12.1,arena_hard,arena_hard_2404,[]
|
| 40 |
-
llama_2_70b_chat,11.6,arena_hard,arena_hard_2404,[]
|
| 41 |
-
vicuna_33b_v1.3,8.6,arena_hard,arena_hard_2404,[]
|
| 42 |
-
gemma_7b_it,7.5,arena_hard,arena_hard_2404,[]
|
| 43 |
-
llama_2_7b_chat,4.6,arena_hard,arena_hard_2404,[]
|
| 44 |
-
gemma_1.1_2b_it,3.4,arena_hard,arena_hard_2404,[]
|
| 45 |
-
gemma_2b_it,3.0,arena_hard,arena_hard_2404,[]
|
| 46 |
-
gpt_4o_2024_05_13,87.9,mixeval,mixeval_240601,[]
|
| 47 |
-
claude_3_opus,88.1,mixeval,mixeval_240601,[]
|
| 48 |
-
gpt_4_turbo_2024_04_09,88.8,mixeval,mixeval_240601,[]
|
| 49 |
-
gemini_1.5_pro_api_0409,84.2,mixeval,mixeval_240601,[]
|
| 50 |
-
yi_large_preview,84.4,mixeval,mixeval_240601,[]
|
| 51 |
-
llama_3_70b_instruct,84.0,mixeval,mixeval_240601,[]
|
| 52 |
-
qwen_max_0428,86.1,mixeval,mixeval_240601,[]
|
| 53 |
-
claude_3_sonnet,81.7,mixeval,mixeval_240601,[]
|
| 54 |
-
reka_core_20240415,83.3,mixeval,mixeval_240601,[]
|
| 55 |
-
mammoth2_8x7b_plus,81.5,mixeval,mixeval_240601,[]
|
| 56 |
-
deepseek_v2,83.7,mixeval,mixeval_240601,[]
|
| 57 |
-
command_r_plus,81.5,mixeval,mixeval_240601,[]
|
| 58 |
-
yi_1.5_34b_chat,81.7,mixeval,mixeval_240601,[]
|
| 59 |
-
mistral_large,84.2,mixeval,mixeval_240601,[]
|
| 60 |
-
qwen1.5_72b_chat,84.1,mixeval,mixeval_240601,[]
|
| 61 |
-
mistral_medium,81.9,mixeval,mixeval_240601,[]
|
| 62 |
-
gemini_1.0_pro,78.9,mixeval,mixeval_240601,[]
|
| 63 |
-
reka_flash_20240226,79.8,mixeval,mixeval_240601,[]
|
| 64 |
-
mistral_small,81.2,mixeval,mixeval_240601,[]
|
| 65 |
-
llama_3_8b_instruct,75.0,mixeval,mixeval_240601,[]
|
| 66 |
-
command_r,77.0,mixeval,mixeval_240601,[]
|
| 67 |
-
qwen1.5_32b_chat,81.0,mixeval,mixeval_240601,[]
|
| 68 |
-
gpt_3.5_turbo_0125,79.7,mixeval,mixeval_240601,[]
|
| 69 |
-
claude_3_haiku,79.7,mixeval,mixeval_240601,[]
|
| 70 |
-
yi_34b_chat,80.1,mixeval,mixeval_240601,[]
|
| 71 |
-
mixtral_8x7b_instruct_v0.1,76.4,mixeval,mixeval_240601,[]
|
| 72 |
-
starling_lm_7b_beta,74.8,mixeval,mixeval_240601,[]
|
| 73 |
-
yi_1.5_9b_chat,74.2,mixeval,mixeval_240601,[]
|
| 74 |
-
gemma_1.1_7b_it,69.6,mixeval,mixeval_240601,[]
|
| 75 |
-
vicuna_33b_v1.3,66.3,mixeval,mixeval_240601,[]
|
| 76 |
-
llama_2_70b_chat,74.6,mixeval,mixeval_240601,[]
|
| 77 |
-
map_neo_instruct_v0.1,70.0,mixeval,mixeval_240601,[]
|
| 78 |
-
mistral_7b_instruct_v0.2,70.0,mixeval,mixeval_240601,[]
|
| 79 |
-
qwen1.5_7b_chat,71.4,mixeval,mixeval_240601,[]
|
| 80 |
-
reka_edge_20240208,68.5,mixeval,mixeval_240601,[]
|
| 81 |
-
zephyr_7b_beta,69.1,mixeval,mixeval_240601,[]
|
| 82 |
-
llama_2_7b_chat,61.7,mixeval,mixeval_240601,[]
|
| 83 |
-
yi_6b_chat,65.6,mixeval,mixeval_240601,[]
|
| 84 |
-
qwen1.5_moe_a2.7b_chat,69.1,mixeval,mixeval_240601,[]
|
| 85 |
-
gemma_1.1_2b_it,51.9,mixeval,mixeval_240601,[]
|
| 86 |
-
vicuna_7b_v1.5,60.3,mixeval,mixeval_240601,[]
|
| 87 |
-
olmo_7b_instruct,55.0,mixeval,mixeval_240601,[]
|
| 88 |
-
qwen1.5_4b_chat,57.2,mixeval,mixeval_240601,[]
|
| 89 |
-
jetmoe_8b_chat,51.6,mixeval,mixeval_240601,[]
|
| 90 |
-
mpt_7b_chat,43.8,mixeval,mixeval_240601,[]
|
| 91 |
-
llama_3_70b,82.2,mixeval,mixeval_240601,[]
|
| 92 |
-
qwen1.5_72b,79.5,mixeval,mixeval_240601,[]
|
| 93 |
-
yi_34b,78.3,mixeval,mixeval_240601,[]
|
| 94 |
-
qwen1.5_32b,77.6,mixeval,mixeval_240601,[]
|
| 95 |
-
mixtral_8x7b,74.0,mixeval,mixeval_240601,[]
|
| 96 |
-
llama_2_70b,73.2,mixeval,mixeval_240601,[]
|
| 97 |
-
qwen1.5_moe_a2.7b,70.2,mixeval,mixeval_240601,[]
|
| 98 |
-
qwen1.5_7b,68.2,mixeval,mixeval_240601,[]
|
| 99 |
-
llama_3_8b,65.1,mixeval,mixeval_240601,[]
|
| 100 |
-
mistral_7b,64.8,mixeval,mixeval_240601,[]
|
| 101 |
-
gemma_7b,64.7,mixeval,mixeval_240601,[]
|
| 102 |
-
yi_6b,63.1,mixeval,mixeval_240601,[]
|
| 103 |
-
qwen1.5_4b,58.2,mixeval,mixeval_240601,[]
|
| 104 |
-
jetmoe_8b,57.1,mixeval,mixeval_240601,[]
|
| 105 |
-
deepseek_7b,52.2,mixeval,mixeval_240601,[]
|
| 106 |
-
phi_2,51.9,mixeval,mixeval_240601,[]
|
| 107 |
-
deepseekmoe_16b,51.4,mixeval,mixeval_240601,[]
|
| 108 |
-
llama_2_7b,43.1,mixeval,mixeval_240601,[]
|
| 109 |
-
gemma_2b,38.9,mixeval,mixeval_240601,[]
|
| 110 |
-
olmo_7b,31.8,mixeval,mixeval_240601,[]
|
| 111 |
-
mpt_7b,30.8,mixeval,mixeval_240601,[]
|
| 112 |
-
gpt_4_0314,0.57,agieval,BLZ_240312,[]
|
| 113 |
-
gpt_4_0613,0.57,agieval,BLZ_240312,[]
|
| 114 |
-
claude_1,0.49700000000000005,agieval,BLZ_240312,[]
|
| 115 |
-
mixtral_8x7b_instruct_v0.1,0.45299999999999996,agieval,BLZ_240312,[]
|
| 116 |
-
yi_34b_chat,0.508,agieval,BLZ_240312,[]
|
| 117 |
-
gpt_3.5_turbo_0314,0.43200000000000005,agieval,BLZ_240312,[]
|
| 118 |
-
vicuna_33b,0.373,agieval,BLZ_240312,[]
|
| 119 |
-
starling_lm_7b_alpha,0.401,agieval,BLZ_240312,[]
|
| 120 |
-
llama_2_70b_chat,0.45,agieval,BLZ_240312,[]
|
| 121 |
-
openhermes_2.5_mistral_7b,0.43,agieval,BLZ_240312,[]
|
| 122 |
-
openchat_3.5,0.42700000000000005,agieval,BLZ_240312,[]
|
| 123 |
-
solar_10.7b_instruct_v1.0,0.47600000000000003,agieval,BLZ_240312,[]
|
| 124 |
-
dolphin_2.2.1_mistral_7b,0.392,agieval,BLZ_240312,[]
|
| 125 |
-
zephyr_7b_beta,0.406,agieval,BLZ_240312,[]
|
| 126 |
-
llama_2_13b_chat,0.336,agieval,BLZ_240312,[]
|
| 127 |
-
vicuna_13b,0.368,agieval,BLZ_240312,[]
|
| 128 |
-
zephyr_7b_alpha,0.38,agieval,BLZ_240312,[]
|
| 129 |
-
qwen_14b_chat,0.396,agieval,BLZ_240312,[]
|
| 130 |
-
llama_2_7b_chat,0.29600000000000004,agieval,BLZ_240312,[]
|
| 131 |
-
mistral_7b_instruct_v0.1,0.335,agieval,BLZ_240312,[]
|
| 132 |
-
vicuna_7b,0.314,agieval,BLZ_240312,[]
|
| 133 |
-
chatglm3_6b,0.414,agieval,BLZ_240312,[]
|
| 134 |
-
chatglm_6b,0.325,agieval,BLZ_240312,[]
|
| 135 |
-
llama_13b,0.205,agieval,BLZ_240312,[]
|
| 136 |
-
gpt_4_0314,0.963,arc_c,BLZ_240312,[]
|
| 137 |
-
mistral_medium,0.899,arc_c,BLZ_240312,[]
|
| 138 |
-
mixtral_8x7b_instruct_v0.1,0.7021999999999999,arc_c,BLZ_240312,[]
|
| 139 |
-
yi_34b_chat,0.6544,arc_c,BLZ_240312,[]
|
| 140 |
-
gpt_3.5_turbo_0314,0.855,arc_c,BLZ_240312,[]
|
| 141 |
-
wizardlm_70b_v1.0,0.6544,arc_c,BLZ_240312,[]
|
| 142 |
-
tulu_2_dpo_70b,0.721,arc_c,BLZ_240312,[]
|
| 143 |
-
vicuna_33b,0.6212,arc_c,BLZ_240312,[]
|
| 144 |
-
starling_lm_7b_alpha,0.6382,arc_c,BLZ_240312,[]
|
| 145 |
-
llama_2_70b_chat,0.6459,arc_c,BLZ_240312,[]
|
| 146 |
-
openhermes_2.5_mistral_7b,0.6493000000000001,arc_c,BLZ_240312,[]
|
| 147 |
-
openchat_3.5,0.6391,arc_c,BLZ_240312,[]
|
| 148 |
-
solar_10.7b_instruct_v1.0,0.7108,arc_c,BLZ_240312,[]
|
| 149 |
-
dolphin_2.2.1_mistral_7b,0.6331,arc_c,BLZ_240312,[]
|
| 150 |
-
wizardlm_13b_v1.2,0.5904,arc_c,BLZ_240312,[]
|
| 151 |
-
zephyr_7b_beta,0.6203,arc_c,BLZ_240312,[]
|
| 152 |
-
mpt_30b_chat,0.5870000000000001,arc_c,BLZ_240312,[]
|
| 153 |
-
codellama_34b_instruct,0.5427000000000001,arc_c,BLZ_240312,[]
|
| 154 |
-
llama_2_13b_chat,0.5904,arc_c,BLZ_240312,[]
|
| 155 |
-
vicuna_13b,0.5708,arc_c,BLZ_240312,[]
|
| 156 |
-
zephyr_7b_alpha,0.6101,arc_c,BLZ_240312,[]
|
| 157 |
-
falcon_180b_chat,0.6945,arc_c,BLZ_240312,[]
|
| 158 |
-
llama_2_7b_chat,0.529,arc_c,BLZ_240312,[]
|
| 159 |
-
mistral_7b_instruct_v0.1,0.5452,arc_c,BLZ_240312,[]
|
| 160 |
-
vicuna_7b,0.5324,arc_c,BLZ_240312,[]
|
| 161 |
-
yi_34bx2_moe_60b,0.7108,arc_c,BLZ_240312,[]
|
| 162 |
-
gpt_4_1106_preview,0.977,alpacav1,BLZ_240312,[]
|
| 163 |
-
gpt_4_0314,0.9528,alpacav1,BLZ_240312,[]
|
| 164 |
-
gpt_4_0613,0.9528,alpacav1,BLZ_240312,[]
|
| 165 |
-
mistral_medium,0.9682999999999999,alpacav1,BLZ_240312,[]
|
| 166 |
-
claude_1,0.8839,alpacav1,BLZ_240312,[]
|
| 167 |
-
claude_2.0,0.9136,alpacav1,BLZ_240312,[]
|
| 168 |
-
gemini_pro_dev_api,0.7966,alpacav1,BLZ_240312,[]
|
| 169 |
-
claude_2.1,0.8708,alpacav1,BLZ_240312,[]
|
| 170 |
-
gpt_3.5_turbo_0613,0.8937,alpacav1,BLZ_240312,[]
|
| 171 |
-
mixtral_8x7b_instruct_v0.1,0.9478,alpacav1,BLZ_240312,[]
|
| 172 |
-
yi_34b_chat,0.9408,alpacav1,BLZ_240312,[]
|
| 173 |
-
gemini_pro,0.7966,alpacav1,BLZ_240312,[]
|
| 174 |
-
gpt_3.5_turbo_0314,0.8937,alpacav1,BLZ_240312,[]
|
| 175 |
-
tulu_2_dpo_70b,0.9503,alpacav1,BLZ_240312,[]
|
| 176 |
-
vicuna_33b,0.8898999999999999,alpacav1,BLZ_240312,[]
|
| 177 |
-
starling_lm_7b_alpha,0.9198999999999999,alpacav1,BLZ_240312,[]
|
| 178 |
-
llama_2_70b_chat,0.9266,alpacav1,BLZ_240312,[]
|
| 179 |
-
openchat_3.5,0.8851,alpacav1,BLZ_240312,[]
|
| 180 |
-
gpt_3.5_turbo_1106,0.8626,alpacav1,BLZ_240312,[]
|
| 181 |
-
wizardlm_13b_v1.2,0.8917,alpacav1,BLZ_240312,[]
|
| 182 |
-
zephyr_7b_beta,0.9059999999999999,alpacav1,BLZ_240312,[]
|
| 183 |
-
llama_2_13b_chat,0.8109000000000001,alpacav1,BLZ_240312,[]
|
| 184 |
-
zephyr_7b_alpha,0.8576,alpacav1,BLZ_240312,[]
|
| 185 |
-
guanaco_33b,0.6596,alpacav1,BLZ_240312,[]
|
| 186 |
-
llama_2_7b_chat,0.7137,alpacav1,BLZ_240312,[]
|
| 187 |
-
chatglm2_6b,0.47130000000000005,alpacav1,BLZ_240312,[]
|
| 188 |
-
openassistant_pythia_12b,0.2596,alpacav1,BLZ_240312,[]
|
| 189 |
-
gpt_4_1106_preview,0.5,alpacav2,BLZ_240312,[]
|
| 190 |
-
gpt_4_0314,0.221,alpacav2,BLZ_240312,[]
|
| 191 |
-
gpt_4_0613,0.158,alpacav2,BLZ_240312,[]
|
| 192 |
-
mistral_medium,0.21899999999999997,alpacav2,BLZ_240312,[]
|
| 193 |
-
claude_1,0.17,alpacav2,BLZ_240312,[]
|
| 194 |
-
claude_2.0,0.172,alpacav2,BLZ_240312,[]
|
| 195 |
-
gemini_pro_dev_api,0.16899999999999998,alpacav2,BLZ_240312,[]
|
| 196 |
-
claude_2.1,0.157,alpacav2,BLZ_240312,[]
|
| 197 |
-
gpt_3.5_turbo_0613,0.141,alpacav2,BLZ_240312,[]
|
| 198 |
-
mixtral_8x7b_instruct_v0.1,0.183,alpacav2,BLZ_240312,[]
|
| 199 |
-
yi_34b_chat,0.297,alpacav2,BLZ_240312,[]
|
| 200 |
-
gemini_pro,0.16899999999999998,alpacav2,BLZ_240312,[]
|
| 201 |
-
claude_instant_1,0.161,alpacav2,BLZ_240312,[]
|
| 202 |
-
gpt_3.5_turbo_0314,0.096,alpacav2,BLZ_240312,[]
|
| 203 |
-
wizardlm_70b_v1.0,0.14400000000000002,alpacav2,BLZ_240312,[]
|
| 204 |
-
tulu_2_dpo_70b,0.16,alpacav2,BLZ_240312,[]
|
| 205 |
-
vicuna_33b,0.127,alpacav2,BLZ_240312,[]
|
| 206 |
-
starling_lm_7b_alpha,0.142,alpacav2,BLZ_240312,[]
|
| 207 |
-
deepseek_llm_67b_chat,0.121,alpacav2,BLZ_240312,[]
|
| 208 |
-
llama_2_70b_chat,0.139,alpacav2,BLZ_240312,[]
|
| 209 |
-
openhermes_2.5_mistral_7b,0.10300000000000001,alpacav2,BLZ_240312,[]
|
| 210 |
-
gpt_3.5_turbo_1106,0.092,alpacav2,BLZ_240312,[]
|
| 211 |
-
dolphin_2.2.1_mistral_7b,0.09,alpacav2,BLZ_240312,[]
|
| 212 |
-
wizardlm_13b_v1.2,0.12,alpacav2,BLZ_240312,[]
|
| 213 |
-
zephyr_7b_beta,0.11,alpacav2,BLZ_240312,[]
|
| 214 |
-
llama_2_13b_chat,0.077,alpacav2,BLZ_240312,[]
|
| 215 |
-
vicuna_13b,0.067,alpacav2,BLZ_240312,[]
|
| 216 |
-
zephyr_7b_alpha,0.084,alpacav2,BLZ_240312,[]
|
| 217 |
-
qwen_14b_chat,0.075,alpacav2,BLZ_240312,[]
|
| 218 |
-
guanaco_33b,0.05,alpacav2,BLZ_240312,[]
|
| 219 |
-
llama_2_7b_chat,0.0496,alpacav2,BLZ_240312,[]
|
| 220 |
-
vicuna_7b,0.048,alpacav2,BLZ_240312,[]
|
| 221 |
-
chatglm2_6b,0.027999999999999997,alpacav2,BLZ_240312,[]
|
| 222 |
-
openassistant_pythia_12b,0.018000000000000002,alpacav2,BLZ_240312,[]
|
| 223 |
-
gpt_4_1106_preview,0.32799999999999996,alpacaeval2_lc,BLZ_240312,[]
|
| 224 |
-
gpt_4_0314,0.21600000000000003,alpacaeval2_lc,BLZ_240312,[]
|
| 225 |
-
gpt_4_0613,0.18600000000000003,alpacaeval2_lc,BLZ_240312,[]
|
| 226 |
-
mistral_medium,0.196,alpacaeval2_lc,BLZ_240312,[]
|
| 227 |
-
claude_1,0.21100000000000002,alpacaeval2_lc,BLZ_240312,[]
|
| 228 |
-
claude_2.0,0.21600000000000003,alpacaeval2_lc,BLZ_240312,[]
|
| 229 |
-
gemini_pro_dev_api,0.172,alpacaeval2_lc,BLZ_240312,[]
|
| 230 |
-
claude_2.1,0.193,alpacaeval2_lc,BLZ_240312,[]
|
| 231 |
-
gpt_3.5_turbo_0613,0.14300000000000002,alpacaeval2_lc,BLZ_240312,[]
|
| 232 |
-
mixtral_8x7b_instruct_v0.1,0.168,alpacaeval2_lc,BLZ_240312,[]
|
| 233 |
-
yi_34b_chat,0.188,alpacaeval2_lc,BLZ_240312,[]
|
| 234 |
-
claude_instant_1,0.195,alpacaeval2_lc,BLZ_240312,[]
|
| 235 |
-
gpt_3.5_turbo_0314,0.156,alpacaeval2_lc,BLZ_240312,[]
|
| 236 |
-
wizardlm_70b_v1.0,0.125,alpacaeval2_lc,BLZ_240312,[]
|
| 237 |
-
tulu_2_dpo_70b,0.151,alpacaeval2_lc,BLZ_240312,[]
|
| 238 |
-
vicuna_33b,0.115,alpacaeval2_lc,BLZ_240312,[]
|
| 239 |
-
starling_lm_7b_alpha,0.10099999999999999,alpacaeval2_lc,BLZ_240312,[]
|
| 240 |
-
deepseek_llm_67b_chat,0.141,alpacaeval2_lc,BLZ_240312,[]
|
| 241 |
-
llama_2_70b_chat,0.10400000000000001,alpacaeval2_lc,BLZ_240312,[]
|
| 242 |
-
openhermes_2.5_mistral_7b,0.126,alpacaeval2_lc,BLZ_240312,[]
|
| 243 |
-
gpt_3.5_turbo_1106,0.155,alpacaeval2_lc,BLZ_240312,[]
|
| 244 |
-
dolphin_2.2.1_mistral_7b,0.10800000000000001,alpacaeval2_lc,BLZ_240312,[]
|
| 245 |
-
wizardlm_13b_v1.2,0.099,alpacaeval2_lc,BLZ_240312,[]
|
| 246 |
-
zephyr_7b_beta,0.102,alpacaeval2_lc,BLZ_240312,[]
|
| 247 |
-
llama_2_13b_chat,0.068,alpacaeval2_lc,BLZ_240312,[]
|
| 248 |
-
vicuna_13b,0.085,alpacaeval2_lc,BLZ_240312,[]
|
| 249 |
-
zephyr_7b_alpha,0.086,alpacaeval2_lc,BLZ_240312,[]
|
| 250 |
-
qwen_14b_chat,0.1,alpacaeval2_lc,BLZ_240312,[]
|
| 251 |
-
llama_2_7b_chat,0.045,alpacaeval2_lc,BLZ_240312,[]
|
| 252 |
-
vicuna_7b,0.06,alpacaeval2_lc,BLZ_240312,[]
|
| 253 |
-
gpt_4_0125_preview,1.0,arena_elo,BLZ_240312,[]
|
| 254 |
-
gpt_4_1106_preview,0.9992019154030327,arena_elo,BLZ_240312,[]
|
| 255 |
-
bard_gemini_pro,0.9768555466879489,arena_elo,BLZ_240312,[]
|
| 256 |
-
gpt_4_0314,0.9497206703910615,arena_elo,BLZ_240312,[]
|
| 257 |
-
gpt_4_0613,0.9273743016759777,arena_elo,BLZ_240312,[]
|
| 258 |
-
mistral_medium,0.9177972865123704,arena_elo,BLZ_240312,[]
|
| 259 |
-
claude_1,0.9169992019154031,arena_elo,BLZ_240312,[]
|
| 260 |
-
claude_2.0,0.9034317637669593,arena_elo,BLZ_240312,[]
|
| 261 |
-
gemini_pro_dev_api,0.8938547486033519,arena_elo,BLZ_240312,[]
|
| 262 |
-
claude_2.1,0.8930566640063847,arena_elo,BLZ_240312,[]
|
| 263 |
-
gpt_3.5_turbo_0613,0.8922585794094174,arena_elo,BLZ_240312,[]
|
| 264 |
-
mixtral_8x7b_instruct_v0.1,0.8922585794094174,arena_elo,BLZ_240312,[]
|
| 265 |
-
yi_34b_chat,0.8898643256185156,arena_elo,BLZ_240312,[]
|
| 266 |
-
gemini_pro,0.8890662410215483,arena_elo,BLZ_240312,[]
|
| 267 |
-
claude_instant_1,0.8850758180367119,arena_elo,BLZ_240312,[]
|
| 268 |
-
gpt_3.5_turbo_0314,0.8818834796488427,arena_elo,BLZ_240312,[]
|
| 269 |
-
wizardlm_70b_v1.0,0.8818834796488427,arena_elo,BLZ_240312,[]
|
| 270 |
-
tulu_2_dpo_70b,0.8810853950518756,arena_elo,BLZ_240312,[]
|
| 271 |
-
vicuna_33b,0.8723064644852354,arena_elo,BLZ_240312,[]
|
| 272 |
-
starling_lm_7b_alpha,0.8699122106943336,arena_elo,BLZ_240312,[]
|
| 273 |
-
deepseek_llm_67b_chat,0.8635275339185954,arena_elo,BLZ_240312,[]
|
| 274 |
-
llama_2_70b_chat,0.8635275339185954,arena_elo,BLZ_240312,[]
|
| 275 |
-
nv_llama2_70b_steerlm_chat,0.8603351955307262,arena_elo,BLZ_240312,[]
|
| 276 |
-
openhermes_2.5_mistral_7b,0.8603351955307262,arena_elo,BLZ_240312,[]
|
| 277 |
-
openchat_3.5,0.8587390263367917,arena_elo,BLZ_240312,[]
|
| 278 |
-
pplx_70b_online,0.8587390263367917,arena_elo,BLZ_240312,[]
|
| 279 |
-
gpt_3.5_turbo_1106,0.8547486033519553,arena_elo,BLZ_240312,[]
|
| 280 |
-
solar_10.7b_instruct_v1.0,0.8499600957701516,arena_elo,BLZ_240312,[]
|
| 281 |
-
dolphin_2.2.1_mistral_7b,0.8499600957701516,arena_elo,BLZ_240312,[]
|
| 282 |
-
wizardlm_13b_v1.2,0.8443735035913806,arena_elo,BLZ_240312,[]
|
| 283 |
-
zephyr_7b_beta,0.8387869114126097,arena_elo,BLZ_240312,[]
|
| 284 |
-
mpt_30b_chat,0.8332003192338387,arena_elo,BLZ_240312,[]
|
| 285 |
-
codellama_34b_instruct,0.8324022346368715,arena_elo,BLZ_240312,[]
|
| 286 |
-
llama_2_13b_chat,0.8316041500399042,arena_elo,BLZ_240312,[]
|
| 287 |
-
vicuna_13b,0.8300079808459697,arena_elo,BLZ_240312,[]
|
| 288 |
-
pplx_7b_online,0.8284118116520351,arena_elo,BLZ_240312,[]
|
| 289 |
-
zephyr_7b_alpha,0.8276137270550679,arena_elo,BLZ_240312,[]
|
| 290 |
-
qwen_14b_chat,0.825219473264166,arena_elo,BLZ_240312,[]
|
| 291 |
-
falcon_180b_chat,0.8236233040702314,arena_elo,BLZ_240312,[]
|
| 292 |
-
guanaco_33b,0.8236233040702314,arena_elo,BLZ_240312,[]
|
| 293 |
-
llama_2_7b_chat,0.8172386272944933,arena_elo,BLZ_240312,[]
|
| 294 |
-
stripedhyena_nous_7b,0.8140462889066241,arena_elo,BLZ_240312,[]
|
| 295 |
-
mistral_7b_instruct_v0.1,0.8028731045490822,arena_elo,BLZ_240312,[]
|
| 296 |
-
palm_chat_bison_001,0.8028731045490822,arena_elo,BLZ_240312,[]
|
| 297 |
-
vicuna_7b,0.8020750199521149,arena_elo,BLZ_240312,[]
|
| 298 |
-
koala_13b,0.770949720670391,arena_elo,BLZ_240312,[]
|
| 299 |
-
chatglm3_6b,0.7661612130885874,arena_elo,BLZ_240312,[]
|
| 300 |
-
gpt4all_13b_snoozy,0.74780526735834,arena_elo,BLZ_240312,[]
|
| 301 |
-
mpt_7b_chat,0.7430167597765364,arena_elo,BLZ_240312,[]
|
| 302 |
-
chatglm2_6b,0.7422186751795691,arena_elo,BLZ_240312,[]
|
| 303 |
-
rwkv_4_raven_14b,0.7382282521947326,arena_elo,BLZ_240312,[]
|
| 304 |
-
alpaca_13b,0.7214684756584198,arena_elo,BLZ_240312,[]
|
| 305 |
-
openassistant_pythia_12b,0.7158818834796489,arena_elo,BLZ_240312,[]
|
| 306 |
-
chatglm_6b,0.704708699122107,arena_elo,BLZ_240312,[]
|
| 307 |
-
fastchat_t5_3b,0.6975259377494014,arena_elo,BLZ_240312,[]
|
| 308 |
-
stablelm_tuned_alpha_7b,0.6743814844373504,arena_elo,BLZ_240312,[]
|
| 309 |
-
dolly_v2_12b,0.6568236233040702,arena_elo,BLZ_240312,[]
|
| 310 |
-
llama_13b,0.6384676775738228,arena_elo,BLZ_240312,[]
|
| 311 |
-
gpt_4_1106_preview,0.8390000000000001,bbh,BLZ_240312,[]
|
| 312 |
-
gpt_4_0314,0.867,bbh,BLZ_240312,[]
|
| 313 |
-
gpt_4_0613,0.867,bbh,BLZ_240312,[]
|
| 314 |
-
claude_1,0.6729999999999999,bbh,BLZ_240312,[]
|
| 315 |
-
gemini_pro_dev_api,0.6559999999999999,bbh,BLZ_240312,[]
|
| 316 |
-
gpt_3.5_turbo_0613,0.71,bbh,BLZ_240312,[]
|
| 317 |
-
mixtral_8x7b_instruct_v0.1,0.67,bbh,BLZ_240312,[]
|
| 318 |
-
yi_34b_chat,0.7170000000000001,bbh,BLZ_240312,[]
|
| 319 |
-
gemini_pro,0.6559999999999999,bbh,BLZ_240312,[]
|
| 320 |
-
tulu_2_dpo_70b,0.66,bbh,BLZ_240312,[]
|
| 321 |
-
vicuna_33b,0.52,bbh,BLZ_240312,[]
|
| 322 |
-
llama_2_70b_chat,0.608,bbh,BLZ_240312,[]
|
| 323 |
-
gpt_3.5_turbo_1106,0.71,bbh,BLZ_240312,[]
|
| 324 |
-
dolphin_2.2.1_mistral_7b,0.598,bbh,BLZ_240312,[]
|
| 325 |
-
llama_2_13b_chat,0.5820000000000001,bbh,BLZ_240312,[]
|
| 326 |
-
vicuna_13b,0.515,bbh,BLZ_240312,[]
|
| 327 |
-
qwen_14b_chat,0.537,bbh,BLZ_240312,[]
|
| 328 |
-
llama_2_7b_chat,0.35600000000000004,bbh,BLZ_240312,[]
|
| 329 |
-
mistral_7b_instruct_v0.1,0.5670000000000001,bbh,BLZ_240312,[]
|
| 330 |
-
vicuna_7b,0.434,bbh,BLZ_240312,[]
|
| 331 |
-
llama_13b,0.379,bbh,BLZ_240312,[]
|
| 332 |
-
gpt_4_1106_preview,0.8604999999999999,eq_benchv2,BLZ_240312,[]
|
| 333 |
-
gpt_4_0314,0.8573000000000001,eq_benchv2,BLZ_240312,[]
|
| 334 |
-
gpt_4_0613,0.8479000000000001,eq_benchv2,BLZ_240312,[]
|
| 335 |
-
mistral_medium,0.8256999999999999,eq_benchv2,BLZ_240312,[]
|
| 336 |
-
claude_1,0.7683,eq_benchv2,BLZ_240312,[]
|
| 337 |
-
claude_2.0,0.7289,eq_benchv2,BLZ_240312,[]
|
| 338 |
-
gemini_pro_dev_api,0.7508,eq_benchv2,BLZ_240312,[]
|
| 339 |
-
claude_2.1,0.7395999999999999,eq_benchv2,BLZ_240312,[]
|
| 340 |
-
gpt_3.5_turbo_0613,0.6934999999999999,eq_benchv2,BLZ_240312,[]
|
| 341 |
-
mixtral_8x7b_instruct_v0.1,0.7237,eq_benchv2,BLZ_240312,[]
|
| 342 |
-
yi_34b_chat,0.7162000000000001,eq_benchv2,BLZ_240312,[]
|
| 343 |
-
claude_instant_1,0.6904,eq_benchv2,BLZ_240312,[]
|
| 344 |
-
gpt_3.5_turbo_0314,0.7067,eq_benchv2,BLZ_240312,[]
|
| 345 |
-
wizardlm_70b_v1.0,0.7128,eq_benchv2,BLZ_240312,[]
|
| 346 |
-
tulu_2_dpo_70b,0.7663,eq_benchv2,BLZ_240312,[]
|
| 347 |
-
vicuna_33b,0.6707,eq_benchv2,BLZ_240312,[]
|
| 348 |
-
starling_lm_7b_alpha,0.7390000000000001,eq_benchv2,BLZ_240312,[]
|
| 349 |
-
deepseek_llm_67b_chat,0.7753,eq_benchv2,BLZ_240312,[]
|
| 350 |
-
llama_2_70b_chat,0.7359,eq_benchv2,BLZ_240312,[]
|
| 351 |
-
openhermes_2.5_mistral_7b,0.6689,eq_benchv2,BLZ_240312,[]
|
| 352 |
-
openchat_3.5,0.7218000000000001,eq_benchv2,BLZ_240312,[]
|
| 353 |
-
pplx_70b_online,0.6279,eq_benchv2,BLZ_240312,[]
|
| 354 |
-
gpt_3.5_turbo_1106,0.7173999999999999,eq_benchv2,BLZ_240312,[]
|
| 355 |
-
solar_10.7b_instruct_v1.0,0.7353000000000001,eq_benchv2,BLZ_240312,[]
|
| 356 |
-
dolphin_2.2.1_mistral_7b,0.6992,eq_benchv2,BLZ_240312,[]
|
| 357 |
-
wizardlm_13b_v1.2,0.6371,eq_benchv2,BLZ_240312,[]
|
| 358 |
-
zephyr_7b_beta,0.5832999999999999,eq_benchv2,BLZ_240312,[]
|
| 359 |
-
codellama_34b_instruct,0.4915,eq_benchv2,BLZ_240312,[]
|
| 360 |
-
llama_2_13b_chat,0.49119999999999997,eq_benchv2,BLZ_240312,[]
|
| 361 |
-
vicuna_13b,0.6739,eq_benchv2,BLZ_240312,[]
|
| 362 |
-
pplx_7b_online,0.4891,eq_benchv2,BLZ_240312,[]
|
| 363 |
-
zephyr_7b_alpha,0.5682,eq_benchv2,BLZ_240312,[]
|
| 364 |
-
qwen_14b_chat,0.6347,eq_benchv2,BLZ_240312,[]
|
| 365 |
-
falcon_180b_chat,0.5682,eq_benchv2,BLZ_240312,[]
|
| 366 |
-
guanaco_33b,0.3611,eq_benchv2,BLZ_240312,[]
|
| 367 |
-
llama_2_7b_chat,0.3632,eq_benchv2,BLZ_240312,[]
|
| 368 |
-
stripedhyena_nous_7b,0.5458,eq_benchv2,BLZ_240312,[]
|
| 369 |
-
mistral_7b_instruct_v0.1,0.5215,eq_benchv2,BLZ_240312,[]
|
| 370 |
-
yi_34bx2_moe_60b,0.7269,eq_benchv2,BLZ_240312,[]
|
| 371 |
-
mixtral_8x7b_instruct_v0.1,0.7641,gpt4all,BLZ_240312,[]
|
| 372 |
-
yi_34b_chat,0.7212999999999999,gpt4all,BLZ_240312,[]
|
| 373 |
-
starling_lm_7b_alpha,0.7272,gpt4all,BLZ_240312,[]
|
| 374 |
-
openhermes_2.5_mistral_7b,0.7312000000000001,gpt4all,BLZ_240312,[]
|
| 375 |
-
openchat_3.5,0.7292000000000001,gpt4all,BLZ_240312,[]
|
| 376 |
-
solar_10.7b_instruct_v1.0,0.7511,gpt4all,BLZ_240312,[]
|
| 377 |
-
dolphin_2.2.1_mistral_7b,0.7223999999999999,gpt4all,BLZ_240312,[]
|
| 378 |
-
zephyr_7b_beta,0.7182999999999999,gpt4all,BLZ_240312,[]
|
| 379 |
-
vicuna_13b,0.631,gpt4all,BLZ_240312,[]
|
| 380 |
-
zephyr_7b_alpha,0.7223999999999999,gpt4all,BLZ_240312,[]
|
| 381 |
-
mistral_7b_instruct_v0.1,0.6795,gpt4all,BLZ_240312,[]
|
| 382 |
-
vicuna_7b,0.61,gpt4all,BLZ_240312,[]
|
| 383 |
-
koala_13b,0.62,gpt4all,BLZ_240312,[]
|
| 384 |
-
gpt4all_13b_snoozy,0.653,gpt4all,BLZ_240312,[]
|
| 385 |
-
mpt_7b_chat,0.648,gpt4all,BLZ_240312,[]
|
| 386 |
-
openassistant_pythia_12b,0.61,gpt4all,BLZ_240312,[]
|
| 387 |
-
fastchat_t5_3b,0.537,gpt4all,BLZ_240312,[]
|
| 388 |
-
stablelm_tuned_alpha_7b,0.513,gpt4all,BLZ_240312,[]
|
| 389 |
-
llama_13b,0.63,gpt4all,BLZ_240312,[]
|
| 390 |
-
mixtral_8x7b_instruct_v0.1,0.7262000000000001,hugging_6,BLZ_240312,[]
|
| 391 |
-
yi_34b_chat,0.6531999999999999,hugging_6,BLZ_240312,[]
|
| 392 |
-
wizardlm_70b_v1.0,0.6125,hugging_6,BLZ_240312,[]
|
| 393 |
-
tulu_2_dpo_70b,0.7376999999999999,hugging_6,BLZ_240312,[]
|
| 394 |
-
vicuna_33b,0.585,hugging_6,BLZ_240312,[]
|
| 395 |
-
starling_lm_7b_alpha,0.6713,hugging_6,BLZ_240312,[]
|
| 396 |
-
llama_2_70b_chat,0.624,hugging_6,BLZ_240312,[]
|
| 397 |
-
openhermes_2.5_mistral_7b,0.6152000000000001,hugging_6,BLZ_240312,[]
|
| 398 |
-
openchat_3.5,0.6124,hugging_6,BLZ_240312,[]
|
| 399 |
-
solar_10.7b_instruct_v1.0,0.742,hugging_6,BLZ_240312,[]
|
| 400 |
-
dolphin_2.2.1_mistral_7b,0.6493000000000001,hugging_6,BLZ_240312,[]
|
| 401 |
-
wizardlm_13b_v1.2,0.5476,hugging_6,BLZ_240312,[]
|
| 402 |
-
zephyr_7b_beta,0.6195,hugging_6,BLZ_240312,[]
|
| 403 |
-
mpt_30b_chat,0.5538000000000001,hugging_6,BLZ_240312,[]
|
| 404 |
-
codellama_34b_instruct,0.5729,hugging_6,BLZ_240312,[]
|
| 405 |
-
llama_2_13b_chat,0.5490999999999999,hugging_6,BLZ_240312,[]
|
| 406 |
-
vicuna_13b,0.5539999999999999,hugging_6,BLZ_240312,[]
|
| 407 |
-
zephyr_7b_alpha,0.595,hugging_6,BLZ_240312,[]
|
| 408 |
-
falcon_180b_chat,0.6785,hugging_6,BLZ_240312,[]
|
| 409 |
-
llama_2_7b_chat,0.5074000000000001,hugging_6,BLZ_240312,[]
|
| 410 |
-
mistral_7b_instruct_v0.1,0.5496,hugging_6,BLZ_240312,[]
|
| 411 |
-
vicuna_7b,0.521,hugging_6,BLZ_240312,[]
|
| 412 |
-
yi_34bx2_moe_60b,0.7672,hugging_6,BLZ_240312,[]
|
| 413 |
-
gpt_4_0314,0.93,llmonitor,BLZ_240312,[]
|
| 414 |
-
gpt_4_0613,0.89,llmonitor,BLZ_240312,[]
|
| 415 |
-
claude_1,0.66,llmonitor,BLZ_240312,[]
|
| 416 |
-
claude_2.0,0.68,llmonitor,BLZ_240312,[]
|
| 417 |
-
gpt_3.5_turbo_0613,0.81,llmonitor,BLZ_240312,[]
|
| 418 |
-
claude_instant_1,0.6,llmonitor,BLZ_240312,[]
|
| 419 |
-
gpt_3.5_turbo_0314,0.79,llmonitor,BLZ_240312,[]
|
| 420 |
-
llama_2_70b_chat,0.6,llmonitor,BLZ_240312,[]
|
| 421 |
-
mpt_30b_chat,0.4,llmonitor,BLZ_240312,[]
|
| 422 |
-
codellama_34b_instruct,0.34,llmonitor,BLZ_240312,[]
|
| 423 |
-
llama_2_13b_chat,0.5,llmonitor,BLZ_240312,[]
|
| 424 |
-
vicuna_13b,0.5,llmonitor,BLZ_240312,[]
|
| 425 |
-
falcon_180b_chat,0.67,llmonitor,BLZ_240312,[]
|
| 426 |
-
guanaco_33b,0.43,llmonitor,BLZ_240312,[]
|
| 427 |
-
llama_2_7b_chat,0.5,llmonitor,BLZ_240312,[]
|
| 428 |
-
mistral_7b_instruct_v0.1,0.57,llmonitor,BLZ_240312,[]
|
| 429 |
-
palm_chat_bison_001,0.57,llmonitor,BLZ_240312,[]
|
| 430 |
-
vicuna_7b,0.41,llmonitor,BLZ_240312,[]
|
| 431 |
-
koala_13b,0.31,llmonitor,BLZ_240312,[]
|
| 432 |
-
mpt_7b_chat,0.43,llmonitor,BLZ_240312,[]
|
| 433 |
-
dolly_v2_12b,0.23,llmonitor,BLZ_240312,[]
|
| 434 |
-
mistral_medium,0.654,magi,BLZ_240312,[]
|
| 435 |
-
gemini_pro_dev_api,0.528,magi,BLZ_240312,[]
|
| 436 |
-
gpt_3.5_turbo_0613,0.455,magi,BLZ_240312,[]
|
| 437 |
-
mixtral_8x7b_instruct_v0.1,0.49560000000000004,magi,BLZ_240312,[]
|
| 438 |
-
yi_34b_chat,0.5821999999999999,magi,BLZ_240312,[]
|
| 439 |
-
gpt_3.5_turbo_0314,0.512,magi,BLZ_240312,[]
|
| 440 |
-
wizardlm_70b_v1.0,0.4476,magi,BLZ_240312,[]
|
| 441 |
-
tulu_2_dpo_70b,0.5212,magi,BLZ_240312,[]
|
| 442 |
-
vicuna_33b,0.3837,magi,BLZ_240312,[]
|
| 443 |
-
starling_lm_7b_alpha,0.4304,magi,BLZ_240312,[]
|
| 444 |
-
deepseek_llm_67b_chat,0.5946,magi,BLZ_240312,[]
|
| 445 |
-
llama_2_70b_chat,0.39899999999999997,magi,BLZ_240312,[]
|
| 446 |
-
openhermes_2.5_mistral_7b,0.4236,magi,BLZ_240312,[]
|
| 447 |
-
openchat_3.5,0.42200000000000004,magi,BLZ_240312,[]
|
| 448 |
-
gpt_3.5_turbo_1106,0.462,magi,BLZ_240312,[]
|
| 449 |
-
solar_10.7b_instruct_v1.0,0.4693,magi,BLZ_240312,[]
|
| 450 |
-
dolphin_2.2.1_mistral_7b,0.3782,magi,BLZ_240312,[]
|
| 451 |
-
wizardlm_13b_v1.2,0.3678,magi,BLZ_240312,[]
|
| 452 |
-
zephyr_7b_beta,0.4042,magi,BLZ_240312,[]
|
| 453 |
-
llama_2_13b_chat,0.37170000000000003,magi,BLZ_240312,[]
|
| 454 |
-
vicuna_13b,0.36560000000000004,magi,BLZ_240312,[]
|
| 455 |
-
zephyr_7b_alpha,0.39899999999999997,magi,BLZ_240312,[]
|
| 456 |
-
qwen_14b_chat,0.4535,magi,BLZ_240312,[]
|
| 457 |
-
guanaco_33b,0.38659999999999994,magi,BLZ_240312,[]
|
| 458 |
-
llama_2_7b_chat,0.35969999999999996,magi,BLZ_240312,[]
|
| 459 |
-
mistral_7b_instruct_v0.1,0.3704,magi,BLZ_240312,[]
|
| 460 |
-
gpt_4_1106_preview,0.805,mmlu,BLZ_240312,[]
|
| 461 |
-
gpt_4_0314,0.8640000000000001,mmlu,BLZ_240312,[]
|
| 462 |
-
mistral_medium,0.753,mmlu,BLZ_240312,[]
|
| 463 |
-
claude_1,0.77,mmlu,BLZ_240312,[]
|
| 464 |
-
claude_2.0,0.785,mmlu,BLZ_240312,[]
|
| 465 |
-
gemini_pro_dev_api,0.718,mmlu,BLZ_240312,[]
|
| 466 |
-
mixtral_8x7b_instruct_v0.1,0.706,mmlu,BLZ_240312,[]
|
| 467 |
-
yi_34b_chat,0.735,mmlu,BLZ_240312,[]
|
| 468 |
-
gemini_pro,0.718,mmlu,BLZ_240312,[]
|
| 469 |
-
claude_instant_1,0.7340000000000001,mmlu,BLZ_240312,[]
|
| 470 |
-
gpt_3.5_turbo_0314,0.7,mmlu,BLZ_240312,[]
|
| 471 |
-
wizardlm_70b_v1.0,0.637,mmlu,BLZ_240312,[]
|
| 472 |
-
tulu_2_dpo_70b,0.698,mmlu,BLZ_240312,[]
|
| 473 |
-
vicuna_33b,0.5920000000000001,mmlu,BLZ_240312,[]
|
| 474 |
-
starling_lm_7b_alpha,0.639,mmlu,BLZ_240312,[]
|
| 475 |
-
deepseek_llm_67b_chat,0.713,mmlu,BLZ_240312,[]
|
| 476 |
-
llama_2_70b_chat,0.63,mmlu,BLZ_240312,[]
|
| 477 |
-
nv_llama2_70b_steerlm_chat,0.685,mmlu,BLZ_240312,[]
|
| 478 |
-
openhermes_2.5_mistral_7b,0.638,mmlu,BLZ_240312,[]
|
| 479 |
-
openchat_3.5,0.643,mmlu,BLZ_240312,[]
|
| 480 |
-
gpt_3.5_turbo_1106,0.6779999999999999,mmlu,BLZ_240312,[]
|
| 481 |
-
solar_10.7b_instruct_v1.0,0.662,mmlu,BLZ_240312,[]
|
| 482 |
-
dolphin_2.2.1_mistral_7b,0.632,mmlu,BLZ_240312,[]
|
| 483 |
-
wizardlm_13b_v1.2,0.527,mmlu,BLZ_240312,[]
|
| 484 |
-
zephyr_7b_beta,0.614,mmlu,BLZ_240312,[]
|
| 485 |
-
mpt_30b_chat,0.504,mmlu,BLZ_240312,[]
|
| 486 |
-
codellama_34b_instruct,0.537,mmlu,BLZ_240312,[]
|
| 487 |
-
llama_2_13b_chat,0.536,mmlu,BLZ_240312,[]
|
| 488 |
-
vicuna_13b,0.5579999999999999,mmlu,BLZ_240312,[]
|
| 489 |
-
zephyr_7b_alpha,0.614,mmlu,BLZ_240312,[]
|
| 490 |
-
qwen_14b_chat,0.665,mmlu,BLZ_240312,[]
|
| 491 |
-
falcon_180b_chat,0.68,mmlu,BLZ_240312,[]
|
| 492 |
-
guanaco_33b,0.5760000000000001,mmlu,BLZ_240312,[]
|
| 493 |
-
llama_2_7b_chat,0.45799999999999996,mmlu,BLZ_240312,[]
|
| 494 |
-
mistral_7b_instruct_v0.1,0.5539999999999999,mmlu,BLZ_240312,[]
|
| 495 |
-
vicuna_7b,0.51,mmlu,BLZ_240312,[]
|
| 496 |
-
koala_13b,0.447,mmlu,BLZ_240312,[]
|
| 497 |
-
gpt4all_13b_snoozy,0.43,mmlu,BLZ_240312,[]
|
| 498 |
-
mpt_7b_chat,0.32,mmlu,BLZ_240312,[]
|
| 499 |
-
chatglm2_6b,0.455,mmlu,BLZ_240312,[]
|
| 500 |
-
rwkv_4_raven_14b,0.256,mmlu,BLZ_240312,[]
|
| 501 |
-
alpaca_13b,0.48100000000000004,mmlu,BLZ_240312,[]
|
| 502 |
-
openassistant_pythia_12b,0.27,mmlu,BLZ_240312,[]
|
| 503 |
-
chatglm_6b,0.361,mmlu,BLZ_240312,[]
|
| 504 |
-
fastchat_t5_3b,0.47700000000000004,mmlu,BLZ_240312,[]
|
| 505 |
-
stablelm_tuned_alpha_7b,0.244,mmlu,BLZ_240312,[]
|
| 506 |
-
dolly_v2_12b,0.257,mmlu,BLZ_240312,[]
|
| 507 |
-
llama_13b,0.47,mmlu,BLZ_240312,[]
|
| 508 |
-
yi_34bx2_moe_60b,0.775,mmlu,BLZ_240312,[]
|
| 509 |
-
gpt_4_0125_preview,0.0929,mt_bench,BLZ_240312,[]
|
| 510 |
-
gpt_4_1106_preview,0.0932,mt_bench,BLZ_240312,[]
|
| 511 |
-
gpt_4_0314,0.08960000000000001,mt_bench,BLZ_240312,[]
|
| 512 |
-
gpt_4_0613,0.09179999999999999,mt_bench,BLZ_240312,[]
|
| 513 |
-
mistral_medium,0.0861,mt_bench,BLZ_240312,[]
|
| 514 |
-
claude_1,0.079,mt_bench,BLZ_240312,[]
|
| 515 |
-
claude_2.0,0.0806,mt_bench,BLZ_240312,[]
|
| 516 |
-
gemini_pro_dev_api,0.08039999999999999,mt_bench,BLZ_240312,[]
|
| 517 |
-
claude_2.1,0.0818,mt_bench,BLZ_240312,[]
|
| 518 |
-
gpt_3.5_turbo_0613,0.0839,mt_bench,BLZ_240312,[]
|
| 519 |
-
mixtral_8x7b_instruct_v0.1,0.083,mt_bench,BLZ_240312,[]
|
| 520 |
-
yi_34b_chat,0.07769999999999999,mt_bench,BLZ_240312,[]
|
| 521 |
-
gemini_pro,0.08039999999999999,mt_bench,BLZ_240312,[]
|
| 522 |
-
claude_instant_1,0.0785,mt_bench,BLZ_240312,[]
|
| 523 |
-
gpt_3.5_turbo_0314,0.0794,mt_bench,BLZ_240312,[]
|
| 524 |
-
wizardlm_70b_v1.0,0.0771,mt_bench,BLZ_240312,[]
|
| 525 |
-
tulu_2_dpo_70b,0.0789,mt_bench,BLZ_240312,[]
|
| 526 |
-
vicuna_33b,0.0712,mt_bench,BLZ_240312,[]
|
| 527 |
-
starling_lm_7b_alpha,0.0809,mt_bench,BLZ_240312,[]
|
| 528 |
-
deepseek_llm_67b_chat,0.08529999999999999,mt_bench,BLZ_240312,[]
|
| 529 |
-
llama_2_70b_chat,0.06860000000000001,mt_bench,BLZ_240312,[]
|
| 530 |
-
nv_llama2_70b_steerlm_chat,0.0754,mt_bench,BLZ_240312,[]
|
| 531 |
-
openhermes_2.5_mistral_7b,0.07690000000000001,mt_bench,BLZ_240312,[]
|
| 532 |
-
openchat_3.5,0.0781,mt_bench,BLZ_240312,[]
|
| 533 |
-
pplx_70b_online,0.0588,mt_bench,BLZ_240312,[]
|
| 534 |
-
gpt_3.5_turbo_1106,0.0832,mt_bench,BLZ_240312,[]
|
| 535 |
-
solar_10.7b_instruct_v1.0,0.0758,mt_bench,BLZ_240312,[]
|
| 536 |
-
wizardlm_13b_v1.2,0.07200000000000001,mt_bench,BLZ_240312,[]
|
| 537 |
-
zephyr_7b_beta,0.07339999999999999,mt_bench,BLZ_240312,[]
|
| 538 |
-
mpt_30b_chat,0.0639,mt_bench,BLZ_240312,[]
|
| 539 |
-
llama_2_13b_chat,0.0665,mt_bench,BLZ_240312,[]
|
| 540 |
-
vicuna_13b,0.06570000000000001,mt_bench,BLZ_240312,[]
|
| 541 |
-
zephyr_7b_alpha,0.0688,mt_bench,BLZ_240312,[]
|
| 542 |
-
qwen_14b_chat,0.0696,mt_bench,BLZ_240312,[]
|
| 543 |
-
guanaco_33b,0.0653,mt_bench,BLZ_240312,[]
|
| 544 |
-
llama_2_7b_chat,0.06269999999999999,mt_bench,BLZ_240312,[]
|
| 545 |
-
mistral_7b_instruct_v0.1,0.0684,mt_bench,BLZ_240312,[]
|
| 546 |
-
palm_chat_bison_001,0.064,mt_bench,BLZ_240312,[]
|
| 547 |
-
vicuna_7b,0.0617,mt_bench,BLZ_240312,[]
|
| 548 |
-
koala_13b,0.0535,mt_bench,BLZ_240312,[]
|
| 549 |
-
gpt4all_13b_snoozy,0.0541,mt_bench,BLZ_240312,[]
|
| 550 |
-
mpt_7b_chat,0.0542,mt_bench,BLZ_240312,[]
|
| 551 |
-
chatglm2_6b,0.0496,mt_bench,BLZ_240312,[]
|
| 552 |
-
rwkv_4_raven_14b,0.0398,mt_bench,BLZ_240312,[]
|
| 553 |
-
alpaca_13b,0.0453,mt_bench,BLZ_240312,[]
|
| 554 |
-
openassistant_pythia_12b,0.0432,mt_bench,BLZ_240312,[]
|
| 555 |
-
chatglm_6b,0.045,mt_bench,BLZ_240312,[]
|
| 556 |
-
fastchat_t5_3b,0.0304,mt_bench,BLZ_240312,[]
|
| 557 |
-
stablelm_tuned_alpha_7b,0.0275,mt_bench,BLZ_240312,[]
|
| 558 |
-
dolly_v2_12b,0.032799999999999996,mt_bench,BLZ_240312,[]
|
| 559 |
-
llama_13b,0.026099999999999998,mt_bench,BLZ_240312,[]
|
| 560 |
-
gpt_4_0613,0.735,mmlu,helm_lite_240610,[]
|
| 561 |
-
llama_3_70b,0.695,mmlu,helm_lite_240610,[]
|
| 562 |
-
mixtral_8x22b,0.701,mmlu,helm_lite_240610,[]
|
| 563 |
-
palmyra_x_v3_72b,0.702,mmlu,helm_lite_240610,[]
|
| 564 |
-
gpt_4_turbo_1106_preview,0.699,mmlu,helm_lite_240610,[]
|
| 565 |
-
palm_2_unicorn,0.702,mmlu,helm_lite_240610,[]
|
| 566 |
-
claude_3_opus_20240229,0.768,mmlu,helm_lite_240610,[]
|
| 567 |
-
qwen1.5_72b,0.647,mmlu,helm_lite_240610,[]
|
| 568 |
-
palmyra_x_v2_33b,0.621,mmlu,helm_lite_240610,[]
|
| 569 |
-
yi_34b,0.65,mmlu,helm_lite_240610,[]
|
| 570 |
-
qwen1.5_32b,0.628,mmlu,helm_lite_240610,[]
|
| 571 |
-
claude_v1.3,0.631,mmlu,helm_lite_240610,[]
|
| 572 |
-
mixtral_8x7b_32k_seqlen,0.649,mmlu,helm_lite_240610,[]
|
| 573 |
-
palm_2_bison,0.608,mmlu,helm_lite_240610,[]
|
| 574 |
-
claude_2.0,0.639,mmlu,helm_lite_240610,[]
|
| 575 |
-
deepseek_llm_chat_67b,0.641,mmlu,helm_lite_240610,[]
|
| 576 |
-
llama_2_70b,0.58,mmlu,helm_lite_240610,[]
|
| 577 |
-
claude_2.1,0.643,mmlu,helm_lite_240610,[]
|
| 578 |
-
gpt_3.5_text_davinci_003,0.555,mmlu,helm_lite_240610,[]
|
| 579 |
-
qwen1.5_14b,0.626,mmlu,helm_lite_240610,[]
|
| 580 |
-
claude_instant_1.2,0.631,mmlu,helm_lite_240610,[]
|
| 581 |
-
llama_3_8b,0.602,mmlu,helm_lite_240610,[]
|
| 582 |
-
gpt_3.5_turbo_0613,0.614,mmlu,helm_lite_240610,[]
|
| 583 |
-
gemma_7b,0.571,mmlu,helm_lite_240610,[]
|
| 584 |
-
claude_3_sonnet_20240229,0.652,mmlu,helm_lite_240610,[]
|
| 585 |
-
gpt_3.5_text_davinci_002,0.568,mmlu,helm_lite_240610,[]
|
| 586 |
-
llama_65b,0.584,mmlu,helm_lite_240610,[]
|
| 587 |
-
mistral_large_2402,0.638,mmlu,helm_lite_240610,[]
|
| 588 |
-
cohere_command,0.525,mmlu,helm_lite_240610,[]
|
| 589 |
-
dbrx_instructruct,0.643,mmlu,helm_lite_240610,[]
|
| 590 |
-
mistral_v0.1_7b,0.584,mmlu,helm_lite_240610,[]
|
| 591 |
-
mistral_small_2402,0.593,mmlu,helm_lite_240610,[]
|
| 592 |
-
mistral_medium_2312,0.618,mmlu,helm_lite_240610,[]
|
| 593 |
-
qwen1.5_7b,0.569,mmlu,helm_lite_240610,[]
|
| 594 |
-
claude_3_haiku_20240307,0.662,mmlu,helm_lite_240610,[]
|
| 595 |
-
yi_6b,0.53,mmlu,helm_lite_240610,[]
|
| 596 |
-
llama_2_13b,0.505,mmlu,helm_lite_240610,[]
|
| 597 |
-
jurassic_2_jumbo_178b,0.483,mmlu,helm_lite_240610,[]
|
| 598 |
-
falcon_40b,0.507,mmlu,helm_lite_240610,[]
|
| 599 |
-
phi_2,0.518,mmlu,helm_lite_240610,[]
|
| 600 |
-
jurassic_2_grande_17b,0.471,mmlu,helm_lite_240610,[]
|
| 601 |
-
llama_2_7b,0.425,mmlu,helm_lite_240610,[]
|
| 602 |
-
luminous_supreme_70b,0.316,mmlu,helm_lite_240610,[]
|
| 603 |
-
cohere_command_light,0.386,mmlu,helm_lite_240610,[]
|
| 604 |
-
luminous_extended_30b,0.248,mmlu,helm_lite_240610,[]
|
| 605 |
-
falcon_7b,0.288,mmlu,helm_lite_240610,[]
|
| 606 |
-
olmo_7b,0.305,mmlu,helm_lite_240610,[]
|
| 607 |
-
luminous_base_13b,0.243,mmlu,helm_lite_240610,[]
|
| 608 |
-
llama_2_70b,0.582,mmlu,helm_classic_240130,[]
|
| 609 |
-
llama_65b,0.584,mmlu,helm_classic_240130,[]
|
| 610 |
-
text_davinci_002,0.568,mmlu,helm_classic_240130,[]
|
| 611 |
-
mistral_v0.1_7b,0.572,mmlu,helm_classic_240130,[]
|
| 612 |
-
cohere_command_beta_52.4b,0.452,mmlu,helm_classic_240130,[]
|
| 613 |
-
text_davinci_003,0.569,mmlu,helm_classic_240130,[]
|
| 614 |
-
jurassic_2_jumbo_178b,0.48,mmlu,helm_classic_240130,[]
|
| 615 |
-
llama_2_13b,0.507,mmlu,helm_classic_240130,[]
|
| 616 |
-
tnlg_v2_530b,0.469,mmlu,helm_classic_240130,[]
|
| 617 |
-
gpt_3.5_turbo_0613,0.391,mmlu,helm_classic_240130,[]
|
| 618 |
-
llama_30b,0.531,mmlu,helm_classic_240130,[]
|
| 619 |
-
anthropic_lm_v4_s3_52b,0.481,mmlu,helm_classic_240130,[]
|
| 620 |
-
gpt_3.5_turbo_0301,0.59,mmlu,helm_classic_240130,[]
|
| 621 |
-
jurassic_2_grande_17b,0.475,mmlu,helm_classic_240130,[]
|
| 622 |
-
palmyra_x_43b,0.609,mmlu,helm_classic_240130,[]
|
| 623 |
-
falcon_40b,0.509,mmlu,helm_classic_240130,[]
|
| 624 |
-
falcon_instruct_40b,0.497,mmlu,helm_classic_240130,[]
|
| 625 |
-
mpt_instruct_30b,0.444,mmlu,helm_classic_240130,[]
|
| 626 |
-
mpt_30b,0.437,mmlu,helm_classic_240130,[]
|
| 627 |
-
j1_grande_v2_beta_17b,0.445,mmlu,helm_classic_240130,[]
|
| 628 |
-
vicuna_v1.3_13b,0.462,mmlu,helm_classic_240130,[]
|
| 629 |
-
cohere_command_beta_6.1b,0.406,mmlu,helm_classic_240130,[]
|
| 630 |
-
cohere_xlarge_v20221108_52.4b,0.382,mmlu,helm_classic_240130,[]
|
| 631 |
-
luminous_supreme_70b,0.38,mmlu,helm_classic_240130,[]
|
| 632 |
-
vicuna_v1.3_7b,0.434,mmlu,helm_classic_240130,[]
|
| 633 |
-
opt_175b,0.318,mmlu,helm_classic_240130,[]
|
| 634 |
-
llama_2_7b,0.431,mmlu,helm_classic_240130,[]
|
| 635 |
-
llama_13b,0.422,mmlu,helm_classic_240130,[]
|
| 636 |
-
instructpalmyra_30b,0.403,mmlu,helm_classic_240130,[]
|
| 637 |
-
cohere_xlarge_v20220609_52.4b,0.353,mmlu,helm_classic_240130,[]
|
| 638 |
-
jurassic_2_large_7.5b,0.339,mmlu,helm_classic_240130,[]
|
| 639 |
-
davinci_175b,0.422,mmlu,helm_classic_240130,[]
|
| 640 |
-
llama_7b,0.321,mmlu,helm_classic_240130,[]
|
| 641 |
-
redpajama_incite_instruct_7b,0.363,mmlu,helm_classic_240130,[]
|
| 642 |
-
j1_jumbo_v1_178b,0.259,mmlu,helm_classic_240130,[]
|
| 643 |
-
glm_130b,0.344,mmlu,helm_classic_240130,[]
|
| 644 |
-
luminous_extended_30b,0.321,mmlu,helm_classic_240130,[]
|
| 645 |
-
opt_66b,0.276,mmlu,helm_classic_240130,[]
|
| 646 |
-
bloom_176b,0.299,mmlu,helm_classic_240130,[]
|
| 647 |
-
j1_grande_v1_17b,0.27,mmlu,helm_classic_240130,[]
|
| 648 |
-
alpaca_7b,0.385,mmlu,helm_classic_240130,[]
|
| 649 |
-
falcon_7b,0.286,mmlu,helm_classic_240130,[]
|
| 650 |
-
redpajama_incite_base_7b,0.302,mmlu,helm_classic_240130,[]
|
| 651 |
-
cohere_large_v20220720_13.1b,0.324,mmlu,helm_classic_240130,[]
|
| 652 |
-
redpajama_incite_instruct_v1_3b,0.257,mmlu,helm_classic_240130,[]
|
| 653 |
-
text_curie_001,0.237,mmlu,helm_classic_240130,[]
|
| 654 |
-
gpt_neox_20b,0.276,mmlu,helm_classic_240130,[]
|
| 655 |
-
luminous_base_13b,0.27,mmlu,helm_classic_240130,[]
|
| 656 |
-
cohere_medium_v20221108_6.1b,0.254,mmlu,helm_classic_240130,[]
|
| 657 |
-
redpajama_incite_base_v1_3b,0.263,mmlu,helm_classic_240130,[]
|
| 658 |
-
tnlg_v2_6.7b,0.242,mmlu,helm_classic_240130,[]
|
| 659 |
-
j1_large_v1_7.5b,0.241,mmlu,helm_classic_240130,[]
|
| 660 |
-
gpt_j_6b,0.249,mmlu,helm_classic_240130,[]
|
| 661 |
-
pythia_12b,0.274,mmlu,helm_classic_240130,[]
|
| 662 |
-
curie_6.7b,0.243,mmlu,helm_classic_240130,[]
|
| 663 |
-
falcon_instruct_7b,0.275,mmlu,helm_classic_240130,[]
|
| 664 |
-
cohere_medium_v20220720_6.1b,0.279,mmlu,helm_classic_240130,[]
|
| 665 |
-
text_babbage_001,0.229,mmlu,helm_classic_240130,[]
|
| 666 |
-
t0pp_11b,0.407,mmlu,helm_classic_240130,[]
|
| 667 |
-
pythia_6.9b,0.236,mmlu,helm_classic_240130,[]
|
| 668 |
-
ul2_20b,0.291,mmlu,helm_classic_240130,[]
|
| 669 |
-
t5_11b,0.29,mmlu,helm_classic_240130,[]
|
| 670 |
-
babbage_1.3b,0.235,mmlu,helm_classic_240130,[]
|
| 671 |
-
cohere_small_v20220720_410m,0.264,mmlu,helm_classic_240130,[]
|
| 672 |
-
ada_350m,0.243,mmlu,helm_classic_240130,[]
|
| 673 |
-
text_ada_001,0.238,mmlu,helm_classic_240130,[]
|
| 674 |
-
yalm_100b,0.243,mmlu,helm_classic_240130,[]
|
| 675 |
-
aya_101,0.029411764705882353,biggen_mwr,biggen_240612,[]
|
| 676 |
-
c4ai_command_r_plus_gptq,0.8382352941176471,biggen_mwr,biggen_240612,[]
|
| 677 |
-
c4ai_command_r_v01,0.6948529411764706,biggen_mwr,biggen_240612,[]
|
| 678 |
-
claude_3_haiku_20240307,0.9252450980392157,biggen_mwr,biggen_240612,[]
|
| 679 |
-
claude_3_opus_20240229,0.9681372549019608,biggen_mwr,biggen_240612,[]
|
| 680 |
-
claude_3_sonnet_20240229,0.9240196078431373,biggen_mwr,biggen_240612,[]
|
| 681 |
-
codellama_13b,0.07598039215686275,biggen_mwr,biggen_240612,[]
|
| 682 |
-
codellama_13b_instruct,0.4276960784313726,biggen_mwr,biggen_240612,[]
|
| 683 |
-
codellama_34b,0.1482843137254902,biggen_mwr,biggen_240612,[]
|
| 684 |
-
codellama_34b_instruct,0.5098039215686274,biggen_mwr,biggen_240612,[]
|
| 685 |
-
codellama_70b,0.18872549019607843,biggen_mwr,biggen_240612,[]
|
| 686 |
-
codellama_70b_instruct,0.27450980392156865,biggen_mwr,biggen_240612,[]
|
| 687 |
-
codellama_7b,0.05514705882352941,biggen_mwr,biggen_240612,[]
|
| 688 |
-
codellama_7b_instruct,0.36519607843137253,biggen_mwr,biggen_240612,[]
|
| 689 |
-
codetulu_2_13b,0.43137254901960786,biggen_mwr,biggen_240612,[]
|
| 690 |
-
codetulu_2_34b,0.5441176470588235,biggen_mwr,biggen_240612,[]
|
| 691 |
-
codetulu_2_7b,0.32598039215686275,biggen_mwr,biggen_240612,[]
|
| 692 |
-
gemini_1.0_pro,0.7107843137254902,biggen_mwr,biggen_240612,[]
|
| 693 |
-
gemini_flash_1.5,0.866421568627451,biggen_mwr,biggen_240612,[]
|
| 694 |
-
gemini_pro_1.5,0.8676470588235294,biggen_mwr,biggen_240612,[]
|
| 695 |
-
gemma_1.1_2b_it,0.33578431372549017,biggen_mwr,biggen_240612,[]
|
| 696 |
-
gemma_1.1_7b_it,0.5551470588235294,biggen_mwr,biggen_240612,[]
|
| 697 |
-
gemma_2b,0.09803921568627451,biggen_mwr,biggen_240612,[]
|
| 698 |
-
gemma_2b_it,0.3333333333333333,biggen_mwr,biggen_240612,[]
|
| 699 |
-
gemma_7b,0.013480392156862746,biggen_mwr,biggen_240612,[]
|
| 700 |
-
gemma_7b_it,0.40931372549019607,biggen_mwr,biggen_240612,[]
|
| 701 |
-
gpt_3.5_turbo_0125,0.7757352941176471,biggen_mwr,biggen_240612,[]
|
| 702 |
-
gpt_3.5_turbo_1106,0.758578431372549,biggen_mwr,biggen_240612,[]
|
| 703 |
-
gpt_4_0125_preview,0.9779411764705882,biggen_mwr,biggen_240612,[]
|
| 704 |
-
gpt_4_1106_preview,0.9889705882352942,biggen_mwr,biggen_240612,[]
|
| 705 |
-
gpt_4_turbo_2024_04_09,0.9558823529411765,biggen_mwr,biggen_240612,[]
|
| 706 |
-
gpt_4o_2024_05_13,0.9436274509803921,biggen_mwr,biggen_240612,[]
|
| 707 |
-
llama_2_13b,0.20220588235294118,biggen_mwr,biggen_240612,[]
|
| 708 |
-
llama_2_13b_chat,0.5968137254901961,biggen_mwr,biggen_240612,[]
|
| 709 |
-
llama_2_70b,0.4656862745098039,biggen_mwr,biggen_240612,[]
|
| 710 |
-
llama_2_70b_chat,0.7205882352941176,biggen_mwr,biggen_240612,[]
|
| 711 |
-
llama_2_7b,0.1446078431372549,biggen_mwr,biggen_240612,[]
|
| 712 |
-
llama_2_7b_chat,0.5355392156862745,biggen_mwr,biggen_240612,[]
|
| 713 |
-
llemma_34b,0.21200980392156862,biggen_mwr,biggen_240612,[]
|
| 714 |
-
llemma_7b,0.11029411764705882,biggen_mwr,biggen_240612,[]
|
| 715 |
-
meta_llama_3_70b,0.36887254901960786,biggen_mwr,biggen_240612,[]
|
| 716 |
-
meta_llama_3_70b_instruct,0.875,biggen_mwr,biggen_240612,[]
|
| 717 |
-
meta_llama_3_8b,0.2377450980392157,biggen_mwr,biggen_240612,[]
|
| 718 |
-
meta_llama_3_8b_instruct,0.7328431372549019,biggen_mwr,biggen_240612,[]
|
| 719 |
-
mistral_7b_instruct_v0.2,0.7156862745098039,biggen_mwr,biggen_240612,[]
|
| 720 |
-
mistral_7b_v0.1,0.3272058823529412,biggen_mwr,biggen_240612,[]
|
| 721 |
-
mistral_7b_v0.2,0.3137254901960784,biggen_mwr,biggen_240612,[]
|
| 722 |
-
mistral_large_hjpark,0.8762254901960784,biggen_mwr,biggen_240612,[]
|
| 723 |
-
mistral_medium_hjpark,0.8970588235294118,biggen_mwr,biggen_240612,[]
|
| 724 |
-
mistral_orpo_alpha,0.5392156862745098,biggen_mwr,biggen_240612,[]
|
| 725 |
-
mistral_orpo_beta,0.5477941176470589,biggen_mwr,biggen_240612,[]
|
| 726 |
-
mixtral_8x22b_instruct_v0.1_awq,0.8198529411764706,biggen_mwr,biggen_240612,[]
|
| 727 |
-
mixtral_8x22b_v0.1_awq,0.5968137254901961,biggen_mwr,biggen_240612,[]
|
| 728 |
-
mixtral_8x7b_instruct_v0.1,0.7647058823529411,biggen_mwr,biggen_240612,[]
|
| 729 |
-
mixtral_8x7b_v0.1,0.5453431372549019,biggen_mwr,biggen_240612,[]
|
| 730 |
-
nous_hermes_2_mistral_7b_dpo,0.571078431372549,biggen_mwr,biggen_240612,[]
|
| 731 |
-
nous_hermes_2_mixtral_8x7b_dpo,0.7095588235294118,biggen_mwr,biggen_240612,[]
|
| 732 |
-
nous_hermes_2_mixtral_8x7b_sft,0.6262254901960784,biggen_mwr,biggen_240612,[]
|
| 733 |
-
nous_hermes_2_yi_34b,0.5906862745098039,biggen_mwr,biggen_240612,[]
|
| 734 |
-
olmo_1b,0.028186274509803922,biggen_mwr,biggen_240612,[]
|
| 735 |
-
olmo_7b,0.07107843137254902,biggen_mwr,biggen_240612,[]
|
| 736 |
-
olmo_7b_instruct,0.30269607843137253,biggen_mwr,biggen_240612,[]
|
| 737 |
-
olmo_7b_sft,0.2549019607843137,biggen_mwr,biggen_240612,[]
|
| 738 |
-
openchat_3.5_0106,0.6825980392156863,biggen_mwr,biggen_240612,[]
|
| 739 |
-
openhermes_2.5_mistral_7b,0.4583333333333333,biggen_mwr,biggen_240612,[]
|
| 740 |
-
openhermes_2_mistral_7b,0.5122549019607843,biggen_mwr,biggen_240612,[]
|
| 741 |
-
orca_2_13b,0.17401960784313725,biggen_mwr,biggen_240612,[]
|
| 742 |
-
orca_2_7b,0.08700980392156862,biggen_mwr,biggen_240612,[]
|
| 743 |
-
phi_1,0.0,biggen_mwr,biggen_240612,[]
|
| 744 |
-
phi_1_5,0.15318627450980393,biggen_mwr,biggen_240612,[]
|
| 745 |
-
phi_2,0.29044117647058826,biggen_mwr,biggen_240612,[]
|
| 746 |
-
phi_3_mini_128k_instruct,0.6911764705882353,biggen_mwr,biggen_240612,[]
|
| 747 |
-
phi_3_mini_4k_instruct,0.7867647058823529,biggen_mwr,biggen_240612,[]
|
| 748 |
-
qwen1.5_0.5b,0.0428921568627451,biggen_mwr,biggen_240612,[]
|
| 749 |
-
qwen1.5_0.5b_chat,0.07965686274509803,biggen_mwr,biggen_240612,[]
|
| 750 |
-
qwen1.5_1.8b,0.12867647058823528,biggen_mwr,biggen_240612,[]
|
| 751 |
-
qwen1.5_1.8b_chat,0.21691176470588236,biggen_mwr,biggen_240612,[]
|
| 752 |
-
qwen1.5_14b,0.3946078431372549,biggen_mwr,biggen_240612,[]
|
| 753 |
-
qwen1.5_14b_chat,0.7267156862745098,biggen_mwr,biggen_240612,[]
|
| 754 |
-
qwen1.5_32b,0.4791666666666667,biggen_mwr,biggen_240612,[]
|
| 755 |
-
qwen1.5_32b_chat,0.8149509803921569,biggen_mwr,biggen_240612,[]
|
| 756 |
-
qwen1.5_4b,0.21323529411764705,biggen_mwr,biggen_240612,[]
|
| 757 |
-
qwen1.5_4b_chat,0.29411764705882354,biggen_mwr,biggen_240612,[]
|
| 758 |
-
qwen1.5_72b,0.5294117647058824,biggen_mwr,biggen_240612,[]
|
| 759 |
-
qwen1.5_72b_chat,0.8713235294117647,biggen_mwr,biggen_240612,[]
|
| 760 |
-
qwen1.5_7b,0.2610294117647059,biggen_mwr,biggen_240612,[]
|
| 761 |
-
qwen1.5_7b_chat,0.6580882352941176,biggen_mwr,biggen_240612,[]
|
| 762 |
-
qwen_110b_chat,0.8848039215686274,biggen_mwr,biggen_240612,[]
|
| 763 |
-
solar_10.7b_instruct_v1.0,0.6862745098039216,biggen_mwr,biggen_240612,[]
|
| 764 |
-
solar_10.7b_v1.0,0.43995098039215685,biggen_mwr,biggen_240612,[]
|
| 765 |
-
starling_lm_7b_alpha,0.6139705882352942,biggen_mwr,biggen_240612,[]
|
| 766 |
-
starling_lm_7b_beta,0.7573529411764706,biggen_mwr,biggen_240612,[]
|
| 767 |
-
tulu_2_13b,0.4313725490196078,biggen_mwr,biggen_240612,[]
|
| 768 |
-
tulu_2_7b,0.3553921568627451,biggen_mwr,biggen_240612,[]
|
| 769 |
-
tulu_2_dpo_13b,0.5833333333333333,biggen_mwr,biggen_240612,[]
|
| 770 |
-
tulu_2_dpo_70b,0.7708333333333334,biggen_mwr,biggen_240612,[]
|
| 771 |
-
tulu_2_dpo_7b,0.4767156862745098,biggen_mwr,biggen_240612,[]
|
| 772 |
-
yi_34b,0.46078431372549017,biggen_mwr,biggen_240612,[]
|
| 773 |
-
yi_34b_chat,0.7720588235294118,biggen_mwr,biggen_240612,[]
|
| 774 |
-
yi_6b,0.17892156862745098,biggen_mwr,biggen_240612,[]
|
| 775 |
-
yi_6b_chat,0.4117647058823529,biggen_mwr,biggen_240612,[]
|
| 776 |
-
zephyr_7b_beta,0.6200980392156863,biggen_mwr,biggen_240612,[]
|
| 777 |
-
zephyr_orpo_141b_a35b_v0.1_awq,0.6311274509803921,biggen_mwr,biggen_240612,[]
|
| 778 |
-
gpt_4o_0513,1293.0,arena_elo,wildbench_240612,[]
|
| 779 |
-
gpt_4_turbo_0409,1251.0,arena_elo,wildbench_240612,[]
|
| 780 |
-
gpt_4_turbo_0125,1239.0,arena_elo,wildbench_240612,[]
|
| 781 |
-
llama_3_70b_inst,1213.0,arena_elo,wildbench_240612,[]
|
| 782 |
-
claude_3_opus,1232.0,arena_elo,wildbench_240612,[]
|
| 783 |
-
claude_3_sonnet,1187.0,arena_elo,wildbench_240612,[]
|
| 784 |
-
qwen1.5_72b_chat,1143.0,arena_elo,wildbench_240612,[]
|
| 785 |
-
command_r_plus,1155.0,arena_elo,wildbench_240612,[]
|
| 786 |
-
claude_3_haiku,1169.0,arena_elo,wildbench_240612,[]
|
| 787 |
-
mistral_large,1158.0,arena_elo,wildbench_240612,[]
|
| 788 |
-
starlinglm_7b_beta,1111.0,arena_elo,wildbench_240612,[]
|
| 789 |
-
llama_3_8b_inst,1144.0,arena_elo,wildbench_240612,[]
|
| 790 |
-
command_r,1106.0,arena_elo,wildbench_240612,[]
|
| 791 |
-
mixtral_8x7b_inst,1114.0,arena_elo,wildbench_240612,[]
|
| 792 |
-
dbrx_instruct,1106.0,arena_elo,wildbench_240612,[]
|
| 793 |
-
mistral_7b_inst_v0.2,1071.0,arena_elo,wildbench_240612,[]
|
| 794 |
-
tulu_2_dpo_70b,1099.0,arena_elo,wildbench_240612,[]
|
| 795 |
-
llama_2_70b_chat,1070.0,arena_elo,wildbench_240612,[]
|
| 796 |
-
qwen1.5_7b_chat,1059.0,arena_elo,wildbench_240612,[]
|
| 797 |
-
gpt_3.5_turbo_0125,1105.0,arena_elo,wildbench_240612,[]
|
| 798 |
-
llama_2_7b_chat,1012.0,arena_elo,wildbench_240612,[]
|
| 799 |
-
gemma_7b_it,1047.0,arena_elo,wildbench_240612,[]
|
| 800 |
-
gemma_2b_it,980.0,arena_elo,wildbench_240612,[]
|
| 801 |
-
gpt_4_turbo_0409,82.6,arena_hard,wildbench_240612,[]
|
| 802 |
-
gpt_4_turbo_0125,78.0,arena_hard,wildbench_240612,[]
|
| 803 |
-
llama_3_70b_inst,41.1,arena_hard,wildbench_240612,[]
|
| 804 |
-
claude_3_opus,60.4,arena_hard,wildbench_240612,[]
|
| 805 |
-
llama3_inst_8b_simpo,33.8,arena_hard,wildbench_240612,[]
|
| 806 |
-
claude_3_sonnet,46.8,arena_hard,wildbench_240612,[]
|
| 807 |
-
qwen1.5_72b_chat,36.1,arena_hard,wildbench_240612,[]
|
| 808 |
-
command_r_plus,33.1,arena_hard,wildbench_240612,[]
|
| 809 |
-
claude_3_haiku,41.5,arena_hard,wildbench_240612,[]
|
| 810 |
-
mistral_large,37.7,arena_hard,wildbench_240612,[]
|
| 811 |
-
starlinglm_7b_beta,23.0,arena_hard,wildbench_240612,[]
|
| 812 |
-
llama_3_8b_inst,20.6,arena_hard,wildbench_240612,[]
|
| 813 |
-
command_r,17.0,arena_hard,wildbench_240612,[]
|
| 814 |
-
mixtral_8x7b_inst,23.4,arena_hard,wildbench_240612,[]
|
| 815 |
-
dbrx_instruct,23.9,arena_hard,wildbench_240612,[]
|
| 816 |
-
tulu_2_dpo_70b,15.0,arena_hard,wildbench_240612,[]
|
| 817 |
-
llama_2_70b_chat,11.6,arena_hard,wildbench_240612,[]
|
| 818 |
-
gpt_3.5_turbo_0125,23.3,arena_hard,wildbench_240612,[]
|
| 819 |
-
llama_2_7b_chat,4.6,arena_hard,wildbench_240612,[]
|
| 820 |
-
gemma_7b_it,7.5,arena_hard,wildbench_240612,[]
|
| 821 |
-
gemma_2b_it,3.0,arena_hard,wildbench_240612,[]
|
| 822 |
-
gpt_4o_0513,57.5,alpacaeval2_lc,wildbench_240612,[]
|
| 823 |
-
gpt_4_turbo_0409,55.0,alpacaeval2_lc,wildbench_240612,[]
|
| 824 |
-
llama_3_70b_inst,34.4,alpacaeval2_lc,wildbench_240612,[]
|
| 825 |
-
claude_3_opus,40.5,alpacaeval2_lc,wildbench_240612,[]
|
| 826 |
-
llama3_inst_8b_simpo,44.7,alpacaeval2_lc,wildbench_240612,[]
|
| 827 |
-
claude_3_sonnet,34.9,alpacaeval2_lc,wildbench_240612,[]
|
| 828 |
-
qwen1.5_72b_chat,36.6,alpacaeval2_lc,wildbench_240612,[]
|
| 829 |
-
mistral_large,32.7,alpacaeval2_lc,wildbench_240612,[]
|
| 830 |
-
llama_3_8b_inst,22.9,alpacaeval2_lc,wildbench_240612,[]
|
| 831 |
-
mixtral_8x7b_inst,23.7,alpacaeval2_lc,wildbench_240612,[]
|
| 832 |
-
dbrx_instruct,25.4,alpacaeval2_lc,wildbench_240612,[]
|
| 833 |
-
mistral_7b_inst_v0.2,17.1,alpacaeval2_lc,wildbench_240612,[]
|
| 834 |
-
tulu_2_dpo_70b,21.2,alpacaeval2_lc,wildbench_240612,[]
|
| 835 |
-
llama_2_70b_chat,14.7,alpacaeval2_lc,wildbench_240612,[]
|
| 836 |
-
qwen1.5_7b_chat,14.7,alpacaeval2_lc,wildbench_240612,[]
|
| 837 |
-
llama_2_7b_chat,5.4,alpacaeval2_lc,wildbench_240612,[]
|
| 838 |
-
gemma_7b_it,10.4,alpacaeval2_lc,wildbench_240612,[]
|
| 839 |
-
gemma_2b_it,5.4,alpacaeval2_lc,wildbench_240612,[]
|
| 840 |
-
gpt_4o_0513,51.3,alpacav2,wildbench_240612,[]
|
| 841 |
-
gpt_4_turbo_0409,46.1,alpacav2,wildbench_240612,[]
|
| 842 |
-
llama_3_70b_inst,33.2,alpacav2,wildbench_240612,[]
|
| 843 |
-
claude_3_opus,29.1,alpacav2,wildbench_240612,[]
|
| 844 |
-
llama3_inst_8b_simpo,40.5,alpacav2,wildbench_240612,[]
|
| 845 |
-
claude_3_sonnet,25.6,alpacav2,wildbench_240612,[]
|
| 846 |
-
qwen1.5_72b_chat,26.5,alpacav2,wildbench_240612,[]
|
| 847 |
-
mistral_large,21.4,alpacav2,wildbench_240612,[]
|
| 848 |
-
llama_3_8b_inst,22.6,alpacav2,wildbench_240612,[]
|
| 849 |
-
mixtral_8x7b_inst,18.3,alpacav2,wildbench_240612,[]
|
| 850 |
-
dbrx_instruct,18.4,alpacav2,wildbench_240612,[]
|
| 851 |
-
mistral_7b_inst_v0.2,14.7,alpacav2,wildbench_240612,[]
|
| 852 |
-
tulu_2_dpo_70b,16.0,alpacav2,wildbench_240612,[]
|
| 853 |
-
llama_2_70b_chat,13.9,alpacav2,wildbench_240612,[]
|
| 854 |
-
qwen1.5_7b_chat,11.8,alpacav2,wildbench_240612,[]
|
| 855 |
-
llama_2_7b_chat,5.0,alpacav2,wildbench_240612,[]
|
| 856 |
-
gemma_7b_it,6.9,alpacav2,wildbench_240612,[]
|
| 857 |
-
gemma_2b_it,3.4,alpacav2,wildbench_240612,[]
|
| 858 |
-
pythia_1b,31.4,arc_c,olmes_260624,[]
|
| 859 |
-
olmo_1b,38.6,arc_c,olmes_260624,[]
|
| 860 |
-
tinyllama_1.1b,38.1,arc_c,olmes_260624,[]
|
| 861 |
-
pythia_6.7b,44.6,arc_c,olmes_260624,[]
|
| 862 |
-
rpj_incite_7b,45.3,arc_c,olmes_260624,[]
|
| 863 |
-
stablelm2_1.6b,50.6,arc_c,olmes_260624,[]
|
| 864 |
-
olmo_7b,46.4,arc_c,olmes_260624,[]
|
| 865 |
-
mpt_7b,45.7,arc_c,olmes_260624,[]
|
| 866 |
-
falcon_7b,49.7,arc_c,olmes_260624,[]
|
| 867 |
-
llama2_7b,54.2,arc_c,olmes_260624,[]
|
| 868 |
-
llama2_13b,67.3,arc_c,olmes_260624,[]
|
| 869 |
-
olmo_1.7_7b,66.9,arc_c,olmes_260624,[]
|
| 870 |
-
llama3_8b,79.3,arc_c,olmes_260624,[]
|
| 871 |
-
mistral_7b_v0.1,78.6,arc_c,olmes_260624,[]
|
| 872 |
-
llama3_70b,93.7,arc_c,olmes_260624,[]
|
| 873 |
-
pythia_1b,31.1,mmlu,olmes_260624,[]
|
| 874 |
-
olmo_1b,33.4,mmlu,olmes_260624,[]
|
| 875 |
-
tinyllama_1.1b,33.6,mmlu,olmes_260624,[]
|
| 876 |
-
pythia_6.7b,37.7,mmlu,olmes_260624,[]
|
| 877 |
-
rpj_incite_7b,40.1,mmlu,olmes_260624,[]
|
| 878 |
-
stablelm2_1.6b,40.4,mmlu,olmes_260624,[]
|
| 879 |
-
olmo_7b,40.5,mmlu,olmes_260624,[]
|
| 880 |
-
mpt_7b,40.6,mmlu,olmes_260624,[]
|
| 881 |
-
falcon_7b,42.1,mmlu,olmes_260624,[]
|
| 882 |
-
llama2_7b,46.2,mmlu,olmes_260624,[]
|
| 883 |
-
llama2_13b,55.8,mmlu,olmes_260624,[]
|
| 884 |
-
olmo_1.7_7b,54.4,mmlu,olmes_260624,[]
|
| 885 |
-
llama3_8b,66.6,mmlu,olmes_260624,[]
|
| 886 |
-
mistral_7b_v0.1,64.0,mmlu,olmes_260624,[]
|
| 887 |
-
llama3_70b,79.8,mmlu,olmes_260624,[]
|
| 888 |
-
pythia_1b,49.0,olmes_average,olmes_260624,[]
|
| 889 |
-
olmo_1b,55.1,olmes_average,olmes_260624,[]
|
| 890 |
-
tinyllama_1.1b,55.4,olmes_average,olmes_260624,[]
|
| 891 |
-
pythia_6.7b,59.1,olmes_average,olmes_260624,[]
|
| 892 |
-
rpj_incite_7b,62.8,olmes_average,olmes_260624,[]
|
| 893 |
-
stablelm2_1.6b,65.1,olmes_average,olmes_260624,[]
|
| 894 |
-
olmo_7b,65.3,olmes_average,olmes_260624,[]
|
| 895 |
-
mpt_7b,65.6,olmes_average,olmes_260624,[]
|
| 896 |
-
falcon_7b,66.9,olmes_average,olmes_260624,[]
|
| 897 |
-
llama2_7b,69.0,olmes_average,olmes_260624,[]
|
| 898 |
-
llama2_13b,74.0,olmes_average,olmes_260624,[]
|
| 899 |
-
olmo_1.7_7b,75.5,olmes_average,olmes_260624,[]
|
| 900 |
-
llama3_8b,78.7,olmes_average,olmes_260624,[]
|
| 901 |
-
mistral_7b_v0.1,79.1,olmes_average,olmes_260624,[]
|
| 902 |
-
llama3_70b,88.4,olmes_average,olmes_260624,[]
|
| 903 |
-
llama_2_70b,0.3753,mmlu_pro,mmlu_pro_240610,[]
|
| 904 |
-
llama_3_8b,0.3536,mmlu_pro,mmlu_pro_240610,[]
|
| 905 |
-
deepseekmath_instruct,0.353,mmlu_pro,mmlu_pro_240610,[]
|
| 906 |
-
gemma_7b,0.3373,mmlu_pro,mmlu_pro_240610,[]
|
| 907 |
-
mistral_7b_v0.1,0.3088,mmlu_pro,mmlu_pro_240610,[]
|
| 908 |
-
mistral_7b_instruct_v0.2,0.3084,mmlu_pro,mmlu_pro_240610,[]
|
| 909 |
-
mistral_7b_v0.2,0.3043,mmlu_pro,mmlu_pro_240610,[]
|
| 910 |
-
qwen1.5_7b_chat,0.2906,mmlu_pro,mmlu_pro_240610,[]
|
| 911 |
-
yi_6b_chat,0.2884,mmlu_pro,mmlu_pro_240610,[]
|
| 912 |
-
yi_6b,0.2651,mmlu_pro,mmlu_pro_240610,[]
|
| 913 |
-
mistral_7b_instruct_v0.1,0.2575,mmlu_pro,mmlu_pro_240610,[]
|
| 914 |
-
llama_2_13b,0.2534,mmlu_pro,mmlu_pro_240610,[]
|
| 915 |
-
llemma_7b,0.2345,mmlu_pro,mmlu_pro_240610,[]
|
| 916 |
-
llama_2_7b,0.2032,mmlu_pro,mmlu_pro_240610,[]
|
| 917 |
-
gpt_4o,0.7255,mmlu_pro,mmlu_pro_240610,[]
|
| 918 |
-
claude_3_opus,0.6845,mmlu_pro,mmlu_pro_240610,[]
|
| 919 |
-
gpt_4_turbo,0.6371,mmlu_pro,mmlu_pro_240610,[]
|
| 920 |
-
gemini_1.5_flash,0.5912,mmlu_pro,mmlu_pro_240610,[]
|
| 921 |
-
yi_large,0.5753,mmlu_pro,mmlu_pro_240610,[]
|
| 922 |
-
claude_3_sonnet,0.568,mmlu_pro,mmlu_pro_240610,[]
|
| 923 |
-
llama_3_70b_instruct,0.562,mmlu_pro,mmlu_pro_240610,[]
|
| 924 |
-
deepseek_v2,0.5481,mmlu_pro,mmlu_pro_240610,[]
|
| 925 |
-
phi_3_medium_4k_instruct,0.5348,mmlu_pro,mmlu_pro_240610,[]
|
| 926 |
-
llama_3_70b,0.5278,mmlu_pro,mmlu_pro_240610,[]
|
| 927 |
-
qwen1.5_72b_chat,0.5162,mmlu_pro,mmlu_pro_240610,[]
|
| 928 |
-
mammoth2_8x7b_plus,0.504,mmlu_pro,mmlu_pro_240610,[]
|
| 929 |
-
qwen1.5_110b,0.4993,mmlu_pro,mmlu_pro_240610,[]
|
| 930 |
-
mammoth2_8b_plus,0.4335,mmlu_pro,mmlu_pro_240610,[]
|
| 931 |
-
mixtral_8x7b_instruct_v0.1,0.4327,mmlu_pro,mmlu_pro_240610,[]
|
| 932 |
-
phi_3_mini_4k_instruct,0.4317,mmlu_pro,mmlu_pro_240610,[]
|
| 933 |
-
yi_34b,0.4303,mmlu_pro,mmlu_pro_240610,[]
|
| 934 |
-
mixtral_8x7b_v0.1,0.4103,mmlu_pro,mmlu_pro_240610,[]
|
| 935 |
-
llama_3_8b_instruct,0.4098,mmlu_pro,mmlu_pro_240610,[]
|
| 936 |
-
mammoth2_7b_plus,0.4085,mmlu_pro,mmlu_pro_240610,[]
|
| 937 |
-
qwen1.5_14b_chat,0.3802,mmlu_pro,mmlu_pro_240610,[]
|
| 938 |
-
c4ai_command_r_v01,0.379,mmlu_pro,mmlu_pro_240610,[]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
cache/agreements_cache_42471fdfe00c7ff9b0aba18b66ab5a5f.csv
DELETED
|
@@ -1,73 +0,0 @@
|
|
| 1 |
-
scenario,scenario_source,ref_scenario,ref_source,corr_type,model_select_strategy,model_subset_size_requested,exp_n,correlation,p_value
|
| 2 |
-
hellaswag,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
|
| 3 |
-
humaneval,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.5270462766947298,0.206507295485425
|
| 4 |
-
mbpp,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.10540925533894598,0.8005421074231263
|
| 5 |
-
winogrande,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,-0.19999999999999998,0.8166666666666667
|
| 6 |
-
grounding,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.9486832980505137,0.02297740150320607
|
| 7 |
-
instruction_following,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.9486832980505137,0.02297740150320607
|
| 8 |
-
planning,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
|
| 9 |
-
reasoning,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
|
| 10 |
-
refinement,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
|
| 11 |
-
safety,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.6,0.23333333333333334
|
| 12 |
-
theory_of_mind,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
|
| 13 |
-
tool_usage,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
|
| 14 |
-
livebench_average,livebench_240701,aggregate,holistic,kendall,top_aggregate,5,0,0.6,0.23333333333333334
|
| 15 |
-
reasoning_average,livebench_240701,aggregate,holistic,kendall,top_aggregate,5,0,0.7378647873726218,0.07697417298126676
|
| 16 |
-
coding_average,livebench_240701,aggregate,holistic,kendall,top_aggregate,5,0,0.5270462766947298,0.206507295485425
|
| 17 |
-
mathematics_average,livebench_240701,aggregate,holistic,kendall,top_aggregate,5,0,0.6,0.23333333333333334
|
| 18 |
-
data_analysis_average,livebench_240701,aggregate,holistic,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
|
| 19 |
-
language_average,livebench_240701,aggregate,holistic,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
|
| 20 |
-
if_average,livebench_240701,aggregate,holistic,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
|
| 21 |
-
arena_hard,arena_hard_2404,aggregate,holistic,kendall,top_aggregate,5,0,0.6,0.23333333333333334
|
| 22 |
-
mixeval,mixeval_240601,aggregate,holistic,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
|
| 23 |
-
agieval,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.7378647873726218,0.07697417298126676
|
| 24 |
-
arc_c,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.6,0.23333333333333334
|
| 25 |
-
alpacav1,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.7378647873726218,0.07697417298126676
|
| 26 |
-
alpacav2,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
|
| 27 |
-
alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.5270462766947298,0.206507295485425
|
| 28 |
-
arena_elo,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
|
| 29 |
-
bbh,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.31622776601683794,0.44848886103153174
|
| 30 |
-
eq_benchv2,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
|
| 31 |
-
gpt4all,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
|
| 32 |
-
hugging_6,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
|
| 33 |
-
llmonitor,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.6,0.23333333333333334
|
| 34 |
-
magi,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
|
| 35 |
-
mmlu,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.6,0.23333333333333334
|
| 36 |
-
mt_bench,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.6,0.23333333333333334
|
| 37 |
-
biggen_mwr,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.6,0.23333333333333334
|
| 38 |
-
aggregate,holistic,hellaswag,BLZ_240312,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
|
| 39 |
-
aggregate,holistic,humaneval,BLZ_240312,kendall,top_aggregate,5,0,0.5270462766947298,0.206507295485425
|
| 40 |
-
aggregate,holistic,mbpp,BLZ_240312,kendall,top_aggregate,5,0,0.10540925533894598,0.8005421074231263
|
| 41 |
-
aggregate,holistic,winogrande,BLZ_240312,kendall,top_aggregate,5,0,-0.19999999999999998,0.8166666666666667
|
| 42 |
-
aggregate,holistic,grounding,biggen_240612,kendall,top_aggregate,5,0,0.9486832980505137,0.02297740150320607
|
| 43 |
-
aggregate,holistic,instruction_following,biggen_240612,kendall,top_aggregate,5,0,0.9486832980505137,0.02297740150320607
|
| 44 |
-
aggregate,holistic,planning,biggen_240612,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
|
| 45 |
-
aggregate,holistic,reasoning,biggen_240612,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
|
| 46 |
-
aggregate,holistic,refinement,biggen_240612,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
|
| 47 |
-
aggregate,holistic,safety,biggen_240612,kendall,top_aggregate,5,0,0.6,0.23333333333333334
|
| 48 |
-
aggregate,holistic,theory_of_mind,biggen_240612,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
|
| 49 |
-
aggregate,holistic,tool_usage,biggen_240612,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
|
| 50 |
-
aggregate,holistic,livebench_average,livebench_240701,kendall,top_aggregate,5,0,0.6,0.23333333333333334
|
| 51 |
-
aggregate,holistic,reasoning_average,livebench_240701,kendall,top_aggregate,5,0,0.7378647873726218,0.07697417298126676
|
| 52 |
-
aggregate,holistic,coding_average,livebench_240701,kendall,top_aggregate,5,0,0.5270462766947298,0.206507295485425
|
| 53 |
-
aggregate,holistic,mathematics_average,livebench_240701,kendall,top_aggregate,5,0,0.6,0.23333333333333334
|
| 54 |
-
aggregate,holistic,data_analysis_average,livebench_240701,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
|
| 55 |
-
aggregate,holistic,language_average,livebench_240701,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
|
| 56 |
-
aggregate,holistic,if_average,livebench_240701,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
|
| 57 |
-
aggregate,holistic,arena_hard,arena_hard_2404,kendall,top_aggregate,5,0,0.6,0.23333333333333334
|
| 58 |
-
aggregate,holistic,mixeval,mixeval_240601,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
|
| 59 |
-
aggregate,holistic,agieval,BLZ_240312,kendall,top_aggregate,5,0,0.7378647873726218,0.07697417298126676
|
| 60 |
-
aggregate,holistic,arc_c,BLZ_240312,kendall,top_aggregate,5,0,0.6,0.23333333333333334
|
| 61 |
-
aggregate,holistic,alpacav1,BLZ_240312,kendall,top_aggregate,5,0,0.7378647873726218,0.07697417298126676
|
| 62 |
-
aggregate,holistic,alpacav2,BLZ_240312,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
|
| 63 |
-
aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,top_aggregate,5,0,0.5270462766947298,0.206507295485425
|
| 64 |
-
aggregate,holistic,arena_elo,BLZ_240312,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
|
| 65 |
-
aggregate,holistic,bbh,BLZ_240312,kendall,top_aggregate,5,0,0.31622776601683794,0.44848886103153174
|
| 66 |
-
aggregate,holistic,eq_benchv2,BLZ_240312,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
|
| 67 |
-
aggregate,holistic,gpt4all,BLZ_240312,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
|
| 68 |
-
aggregate,holistic,hugging_6,BLZ_240312,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
|
| 69 |
-
aggregate,holistic,llmonitor,BLZ_240312,kendall,top_aggregate,5,0,0.6,0.23333333333333334
|
| 70 |
-
aggregate,holistic,magi,BLZ_240312,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
|
| 71 |
-
aggregate,holistic,mmlu,BLZ_240312,kendall,top_aggregate,5,0,0.6,0.23333333333333334
|
| 72 |
-
aggregate,holistic,mt_bench,BLZ_240312,kendall,top_aggregate,5,0,0.6,0.23333333333333334
|
| 73 |
-
aggregate,holistic,biggen_mwr,biggen_240612,kendall,top_aggregate,5,0,0.6,0.23333333333333334
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
cache/agreements_cache_6ac32881b7d0a3bf6d8762ff242ff449.csv
DELETED
|
@@ -1,721 +0,0 @@
|
|
| 1 |
-
scenario,scenario_source,ref_scenario,ref_source,corr_type,model_select_strategy,model_subset_size_requested,exp_n,correlation,p_value
|
| 2 |
-
hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
|
| 3 |
-
hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 4 |
-
hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 5 |
-
hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
|
| 6 |
-
hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
|
| 7 |
-
hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334
|
| 8 |
-
hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.39999999999999997,0.48333333333333334
|
| 9 |
-
hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.0,1.0
|
| 10 |
-
hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.19999999999999998,0.8166666666666667
|
| 11 |
-
hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 12 |
-
humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.19999999999999998,0.8166666666666667
|
| 13 |
-
humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 14 |
-
humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 15 |
-
humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.31622776601683794,0.44848886103153174
|
| 16 |
-
humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
|
| 17 |
-
humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334
|
| 18 |
-
humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.39999999999999997,0.48333333333333334
|
| 19 |
-
humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
|
| 20 |
-
humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.39999999999999997,0.48333333333333334
|
| 21 |
-
humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.39999999999999997,0.48333333333333334
|
| 22 |
-
mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666
|
| 23 |
-
mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.5270462766947298,0.206507295485425
|
| 24 |
-
mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
|
| 25 |
-
mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
|
| 26 |
-
mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 27 |
-
mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.5270462766947298,0.206507295485425
|
| 28 |
-
mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 29 |
-
mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334
|
| 30 |
-
mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.39999999999999997,0.48333333333333334
|
| 31 |
-
mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,9,-0.10540925533894598,0.8005421074231263
|
| 32 |
-
winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,0,-0.10540925533894596,0.8005421074231263
|
| 33 |
-
winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 34 |
-
winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 35 |
-
winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 36 |
-
winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.19999999999999998,0.8166666666666667
|
| 37 |
-
winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 38 |
-
winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.39999999999999997,0.48333333333333334
|
| 39 |
-
winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.0,1.0
|
| 40 |
-
winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.0,1.0
|
| 41 |
-
winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 42 |
-
grounding,biggen_240612,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
|
| 43 |
-
grounding,biggen_240612,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 44 |
-
grounding,biggen_240612,aggregate,holistic,kendall,random,5,2,0.39999999999999997,0.48333333333333334
|
| 45 |
-
grounding,biggen_240612,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 46 |
-
grounding,biggen_240612,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 47 |
-
grounding,biggen_240612,aggregate,holistic,kendall,random,5,5,0.9486832980505137,0.02297740150320607
|
| 48 |
-
grounding,biggen_240612,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
|
| 49 |
-
grounding,biggen_240612,aggregate,holistic,kendall,random,5,7,0.19999999999999998,0.8166666666666667
|
| 50 |
-
grounding,biggen_240612,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
|
| 51 |
-
grounding,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 52 |
-
instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,0,0.19999999999999998,0.8166666666666667
|
| 53 |
-
instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 54 |
-
instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,2,0.0,1.0
|
| 55 |
-
instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 56 |
-
instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 57 |
-
instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,5,0.9486832980505137,0.02297740150320607
|
| 58 |
-
instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
|
| 59 |
-
instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,7,-0.10540925533894598,0.8005421074231263
|
| 60 |
-
instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,8,0.9486832980505137,0.02297740150320607
|
| 61 |
-
instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 62 |
-
planning,biggen_240612,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
|
| 63 |
-
planning,biggen_240612,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
|
| 64 |
-
planning,biggen_240612,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
|
| 65 |
-
planning,biggen_240612,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
|
| 66 |
-
planning,biggen_240612,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
|
| 67 |
-
planning,biggen_240612,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334
|
| 68 |
-
planning,biggen_240612,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
|
| 69 |
-
planning,biggen_240612,aggregate,holistic,kendall,random,5,7,0.19999999999999998,0.8166666666666667
|
| 70 |
-
planning,biggen_240612,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
|
| 71 |
-
planning,biggen_240612,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
|
| 72 |
-
reasoning,biggen_240612,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
|
| 73 |
-
reasoning,biggen_240612,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 74 |
-
reasoning,biggen_240612,aggregate,holistic,kendall,random,5,2,0.7378647873726218,0.07697417298126676
|
| 75 |
-
reasoning,biggen_240612,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 76 |
-
reasoning,biggen_240612,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
|
| 77 |
-
reasoning,biggen_240612,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
|
| 78 |
-
reasoning,biggen_240612,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
|
| 79 |
-
reasoning,biggen_240612,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334
|
| 80 |
-
reasoning,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 81 |
-
reasoning,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 82 |
-
refinement,biggen_240612,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
|
| 83 |
-
refinement,biggen_240612,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 84 |
-
refinement,biggen_240612,aggregate,holistic,kendall,random,5,2,0.19999999999999998,0.8166666666666667
|
| 85 |
-
refinement,biggen_240612,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 86 |
-
refinement,biggen_240612,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
|
| 87 |
-
refinement,biggen_240612,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334
|
| 88 |
-
refinement,biggen_240612,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
|
| 89 |
-
refinement,biggen_240612,aggregate,holistic,kendall,random,5,7,-0.19999999999999998,0.8166666666666667
|
| 90 |
-
refinement,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 91 |
-
refinement,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 92 |
-
safety,biggen_240612,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
|
| 93 |
-
safety,biggen_240612,aggregate,holistic,kendall,random,5,1,0.19999999999999998,0.8166666666666667
|
| 94 |
-
safety,biggen_240612,aggregate,holistic,kendall,random,5,2,-0.6,0.23333333333333334
|
| 95 |
-
safety,biggen_240612,aggregate,holistic,kendall,random,5,3,0.0,1.0
|
| 96 |
-
safety,biggen_240612,aggregate,holistic,kendall,random,5,4,0.39999999999999997,0.48333333333333334
|
| 97 |
-
safety,biggen_240612,aggregate,holistic,kendall,random,5,5,0.0,1.0
|
| 98 |
-
safety,biggen_240612,aggregate,holistic,kendall,random,5,6,0.39999999999999997,0.48333333333333334
|
| 99 |
-
safety,biggen_240612,aggregate,holistic,kendall,random,5,7,-0.6,0.23333333333333334
|
| 100 |
-
safety,biggen_240612,aggregate,holistic,kendall,random,5,8,-0.19999999999999998,0.8166666666666667
|
| 101 |
-
safety,biggen_240612,aggregate,holistic,kendall,random,5,9,0.39999999999999997,0.48333333333333334
|
| 102 |
-
theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
|
| 103 |
-
theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 104 |
-
theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,2,0.19999999999999998,0.8166666666666667
|
| 105 |
-
theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 106 |
-
theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
|
| 107 |
-
theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 108 |
-
theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
|
| 109 |
-
theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,7,-0.19999999999999998,0.8166666666666667
|
| 110 |
-
theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
|
| 111 |
-
theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 112 |
-
tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
|
| 113 |
-
tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 114 |
-
tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,2,0.9999999999999999,0.016666666666666666
|
| 115 |
-
tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 116 |
-
tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
|
| 117 |
-
tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
|
| 118 |
-
tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 119 |
-
tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,7,0.0,1.0
|
| 120 |
-
tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 121 |
-
tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 122 |
-
livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
|
| 123 |
-
livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 124 |
-
livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
|
| 125 |
-
livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.39999999999999997,0.48333333333333334
|
| 126 |
-
livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
|
| 127 |
-
livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 128 |
-
livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
|
| 129 |
-
livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 130 |
-
livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334
|
| 131 |
-
livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 132 |
-
reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
|
| 133 |
-
reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.7378647873726218,0.07697417298126676
|
| 134 |
-
reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
|
| 135 |
-
reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.5270462766947298,0.206507295485425
|
| 136 |
-
reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.7378647873726218,0.07697417298126676
|
| 137 |
-
reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.7378647873726218,0.07697417298126676
|
| 138 |
-
reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.7378647873726218,0.07697417298126676
|
| 139 |
-
reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 140 |
-
reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.7378647873726218,0.07697417298126676
|
| 141 |
-
reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.7378647873726218,0.07697417298126676
|
| 142 |
-
coding_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
|
| 143 |
-
coding_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 144 |
-
coding_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
|
| 145 |
-
coding_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.31622776601683794,0.44848886103153174
|
| 146 |
-
coding_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.5270462766947298,0.206507295485425
|
| 147 |
-
coding_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 148 |
-
coding_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.5270462766947298,0.206507295485425
|
| 149 |
-
coding_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7378647873726218,0.07697417298126676
|
| 150 |
-
coding_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.5270462766947298,0.206507295485425
|
| 151 |
-
coding_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 152 |
-
mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
|
| 153 |
-
mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 154 |
-
mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
|
| 155 |
-
mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.39999999999999997,0.48333333333333334
|
| 156 |
-
mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 157 |
-
mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
|
| 158 |
-
mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
|
| 159 |
-
mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 160 |
-
mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 161 |
-
mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 162 |
-
data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
|
| 163 |
-
data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 164 |
-
data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 165 |
-
data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
|
| 166 |
-
data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 167 |
-
data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 168 |
-
data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
|
| 169 |
-
data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
|
| 170 |
-
data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 171 |
-
data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 172 |
-
language_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
|
| 173 |
-
language_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
|
| 174 |
-
language_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
|
| 175 |
-
language_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
|
| 176 |
-
language_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 177 |
-
language_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
|
| 178 |
-
language_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 179 |
-
language_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 180 |
-
language_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 181 |
-
language_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
|
| 182 |
-
if_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
|
| 183 |
-
if_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
|
| 184 |
-
if_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 185 |
-
if_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.0,1.0
|
| 186 |
-
if_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.0,1.0
|
| 187 |
-
if_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
|
| 188 |
-
if_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.19999999999999998,0.8166666666666667
|
| 189 |
-
if_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334
|
| 190 |
-
if_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.0,1.0
|
| 191 |
-
if_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
|
| 192 |
-
arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666
|
| 193 |
-
arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,1,0.39999999999999997,0.48333333333333334
|
| 194 |
-
arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 195 |
-
arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 196 |
-
arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 197 |
-
arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
|
| 198 |
-
arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
|
| 199 |
-
arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 200 |
-
arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
|
| 201 |
-
arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,9,0.9486832980505138,0.02297740150320607
|
| 202 |
-
mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
|
| 203 |
-
mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 204 |
-
mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 205 |
-
mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 206 |
-
mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 207 |
-
mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
|
| 208 |
-
mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 209 |
-
mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
|
| 210 |
-
mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 211 |
-
mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 212 |
-
agieval,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.5270462766947299,0.206507295485425
|
| 213 |
-
agieval,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 214 |
-
agieval,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
|
| 215 |
-
agieval,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 216 |
-
agieval,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 217 |
-
agieval,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 218 |
-
agieval,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
|
| 219 |
-
agieval,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334
|
| 220 |
-
agieval,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.19999999999999998,0.8166666666666667
|
| 221 |
-
agieval,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
|
| 222 |
-
arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.5270462766947298,0.206507295485425
|
| 223 |
-
arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 224 |
-
arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.9999999999999999,0.016666666666666666
|
| 225 |
-
arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 226 |
-
arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 227 |
-
arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 228 |
-
arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 229 |
-
arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
|
| 230 |
-
arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.19999999999999998,0.8166666666666667
|
| 231 |
-
arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 232 |
-
alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.19999999999999998,0.8166666666666667
|
| 233 |
-
alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 234 |
-
alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
|
| 235 |
-
alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 236 |
-
alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 237 |
-
alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334
|
| 238 |
-
alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.19999999999999998,0.8166666666666667
|
| 239 |
-
alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334
|
| 240 |
-
alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
|
| 241 |
-
alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 242 |
-
alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
|
| 243 |
-
alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 244 |
-
alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 245 |
-
alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 246 |
-
alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 247 |
-
alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
|
| 248 |
-
alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 249 |
-
alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
|
| 250 |
-
alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
|
| 251 |
-
alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 252 |
-
alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.5270462766947299,0.206507295485425
|
| 253 |
-
alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.39999999999999997,0.48333333333333334
|
| 254 |
-
alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 255 |
-
alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
|
| 256 |
-
alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
|
| 257 |
-
alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
|
| 258 |
-
alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 259 |
-
alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334
|
| 260 |
-
alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.19999999999999998,0.8166666666666667
|
| 261 |
-
alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 262 |
-
arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666
|
| 263 |
-
arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 264 |
-
arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,2,1.0,0.019176729141549043
|
| 265 |
-
arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 266 |
-
arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
|
| 267 |
-
arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
|
| 268 |
-
arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
|
| 269 |
-
arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
|
| 270 |
-
arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
|
| 271 |
-
arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 272 |
-
bbh,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
|
| 273 |
-
bbh,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 274 |
-
bbh,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 275 |
-
bbh,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 276 |
-
bbh,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 277 |
-
bbh,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 278 |
-
bbh,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.9486832980505137,0.02297740150320607
|
| 279 |
-
bbh,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.19999999999999998,0.8166666666666667
|
| 280 |
-
bbh,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.0,1.0
|
| 281 |
-
bbh,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 282 |
-
eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
|
| 283 |
-
eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
|
| 284 |
-
eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
|
| 285 |
-
eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 286 |
-
eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 287 |
-
eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
|
| 288 |
-
eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
|
| 289 |
-
eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.5270462766947299,0.206507295485425
|
| 290 |
-
eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 291 |
-
eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
|
| 292 |
-
gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
|
| 293 |
-
gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.0,1.0
|
| 294 |
-
gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 295 |
-
gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 296 |
-
gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
|
| 297 |
-
gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7378647873726218,0.07697417298126676
|
| 298 |
-
gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
|
| 299 |
-
gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334
|
| 300 |
-
gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
|
| 301 |
-
gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.39999999999999997,0.48333333333333334
|
| 302 |
-
hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
|
| 303 |
-
hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 304 |
-
hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.19999999999999998,0.8166666666666667
|
| 305 |
-
hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 306 |
-
hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
|
| 307 |
-
hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334
|
| 308 |
-
hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.39999999999999997,0.48333333333333334
|
| 309 |
-
hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334
|
| 310 |
-
hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.0,1.0
|
| 311 |
-
hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.39999999999999997,0.48333333333333334
|
| 312 |
-
llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.8366600265340756,0.05220363534131463
|
| 313 |
-
llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 314 |
-
llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 315 |
-
llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
|
| 316 |
-
llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
|
| 317 |
-
llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
|
| 318 |
-
llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7378647873726218,0.07697417298126676
|
| 319 |
-
llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.5270462766947298,0.206507295485425
|
| 320 |
-
llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.3333333333333333,0.4349833603383296
|
| 321 |
-
llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.39999999999999997,0.48333333333333334
|
| 322 |
-
magi,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
|
| 323 |
-
magi,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.5270462766947299,0.206507295485425
|
| 324 |
-
magi,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
|
| 325 |
-
magi,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 326 |
-
magi,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 327 |
-
magi,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
|
| 328 |
-
magi,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.10540925533894596,0.8005421074231263
|
| 329 |
-
magi,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334
|
| 330 |
-
magi,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.31622776601683794,0.44848886103153174
|
| 331 |
-
magi,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 332 |
-
mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
|
| 333 |
-
mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 334 |
-
mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.19999999999999998,0.8166666666666667
|
| 335 |
-
mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 336 |
-
mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.39999999999999997,0.48333333333333334
|
| 337 |
-
mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
|
| 338 |
-
mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
|
| 339 |
-
mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
|
| 340 |
-
mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334
|
| 341 |
-
mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 342 |
-
mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
|
| 343 |
-
mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 344 |
-
mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 345 |
-
mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 346 |
-
mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
|
| 347 |
-
mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 348 |
-
mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
|
| 349 |
-
mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
|
| 350 |
-
mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
|
| 351 |
-
mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 352 |
-
biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
|
| 353 |
-
biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,1,0.39999999999999997,0.48333333333333334
|
| 354 |
-
biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,2,0.0,1.0
|
| 355 |
-
biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
|
| 356 |
-
biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,4,0.39999999999999997,0.48333333333333334
|
| 357 |
-
biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 358 |
-
biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,6,0.39999999999999997,0.48333333333333334
|
| 359 |
-
biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
|
| 360 |
-
biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334
|
| 361 |
-
biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
|
| 362 |
-
aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,0,0.39999999999999997,0.48333333333333334
|
| 363 |
-
aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 364 |
-
aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 365 |
-
aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,3,0.6,0.23333333333333334
|
| 366 |
-
aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,4,0.6,0.23333333333333334
|
| 367 |
-
aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,5,0.39999999999999997,0.48333333333333334
|
| 368 |
-
aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,6,0.39999999999999997,0.48333333333333334
|
| 369 |
-
aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,7,0.0,1.0
|
| 370 |
-
aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,8,0.19999999999999998,0.8166666666666667
|
| 371 |
-
aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 372 |
-
aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,0,0.19999999999999998,0.8166666666666667
|
| 373 |
-
aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 374 |
-
aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 375 |
-
aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,3,0.31622776601683794,0.44848886103153174
|
| 376 |
-
aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
|
| 377 |
-
aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,5,0.39999999999999997,0.48333333333333334
|
| 378 |
-
aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,6,0.39999999999999997,0.48333333333333334
|
| 379 |
-
aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,7,0.9999999999999999,0.016666666666666666
|
| 380 |
-
aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,8,0.39999999999999997,0.48333333333333334
|
| 381 |
-
aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,9,0.39999999999999997,0.48333333333333334
|
| 382 |
-
aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,0,0.9999999999999999,0.016666666666666666
|
| 383 |
-
aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,1,0.5270462766947298,0.206507295485425
|
| 384 |
-
aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,2,0.6,0.23333333333333334
|
| 385 |
-
aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,3,0.6,0.23333333333333334
|
| 386 |
-
aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 387 |
-
aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,5,0.5270462766947298,0.206507295485425
|
| 388 |
-
aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 389 |
-
aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,7,0.39999999999999997,0.48333333333333334
|
| 390 |
-
aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,8,0.39999999999999997,0.48333333333333334
|
| 391 |
-
aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,9,-0.10540925533894598,0.8005421074231263
|
| 392 |
-
aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,0,-0.10540925533894596,0.8005421074231263
|
| 393 |
-
aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 394 |
-
aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 395 |
-
aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 396 |
-
aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,4,0.19999999999999998,0.8166666666666667
|
| 397 |
-
aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 398 |
-
aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,6,0.39999999999999997,0.48333333333333334
|
| 399 |
-
aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,7,0.0,1.0
|
| 400 |
-
aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,8,0.0,1.0
|
| 401 |
-
aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 402 |
-
aggregate,holistic,grounding,biggen_240612,kendall,random,5,0,0.39999999999999997,0.48333333333333334
|
| 403 |
-
aggregate,holistic,grounding,biggen_240612,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 404 |
-
aggregate,holistic,grounding,biggen_240612,kendall,random,5,2,0.39999999999999997,0.48333333333333334
|
| 405 |
-
aggregate,holistic,grounding,biggen_240612,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 406 |
-
aggregate,holistic,grounding,biggen_240612,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 407 |
-
aggregate,holistic,grounding,biggen_240612,kendall,random,5,5,0.9486832980505137,0.02297740150320607
|
| 408 |
-
aggregate,holistic,grounding,biggen_240612,kendall,random,5,6,0.9999999999999999,0.016666666666666666
|
| 409 |
-
aggregate,holistic,grounding,biggen_240612,kendall,random,5,7,0.19999999999999998,0.8166666666666667
|
| 410 |
-
aggregate,holistic,grounding,biggen_240612,kendall,random,5,8,0.9999999999999999,0.016666666666666666
|
| 411 |
-
aggregate,holistic,grounding,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 412 |
-
aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,0,0.19999999999999998,0.8166666666666667
|
| 413 |
-
aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 414 |
-
aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,2,0.0,1.0
|
| 415 |
-
aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 416 |
-
aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 417 |
-
aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,5,0.9486832980505137,0.02297740150320607
|
| 418 |
-
aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,6,0.9999999999999999,0.016666666666666666
|
| 419 |
-
aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,7,-0.10540925533894598,0.8005421074231263
|
| 420 |
-
aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,8,0.9486832980505137,0.02297740150320607
|
| 421 |
-
aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 422 |
-
aggregate,holistic,planning,biggen_240612,kendall,random,5,0,0.6,0.23333333333333334
|
| 423 |
-
aggregate,holistic,planning,biggen_240612,kendall,random,5,1,0.6,0.23333333333333334
|
| 424 |
-
aggregate,holistic,planning,biggen_240612,kendall,random,5,2,0.6,0.23333333333333334
|
| 425 |
-
aggregate,holistic,planning,biggen_240612,kendall,random,5,3,0.6,0.23333333333333334
|
| 426 |
-
aggregate,holistic,planning,biggen_240612,kendall,random,5,4,0.9999999999999999,0.016666666666666666
|
| 427 |
-
aggregate,holistic,planning,biggen_240612,kendall,random,5,5,0.39999999999999997,0.48333333333333334
|
| 428 |
-
aggregate,holistic,planning,biggen_240612,kendall,random,5,6,0.6,0.23333333333333334
|
| 429 |
-
aggregate,holistic,planning,biggen_240612,kendall,random,5,7,0.19999999999999998,0.8166666666666667
|
| 430 |
-
aggregate,holistic,planning,biggen_240612,kendall,random,5,8,0.9999999999999999,0.016666666666666666
|
| 431 |
-
aggregate,holistic,planning,biggen_240612,kendall,random,5,9,0.6,0.23333333333333334
|
| 432 |
-
aggregate,holistic,reasoning,biggen_240612,kendall,random,5,0,0.39999999999999997,0.48333333333333334
|
| 433 |
-
aggregate,holistic,reasoning,biggen_240612,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 434 |
-
aggregate,holistic,reasoning,biggen_240612,kendall,random,5,2,0.7378647873726218,0.07697417298126676
|
| 435 |
-
aggregate,holistic,reasoning,biggen_240612,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 436 |
-
aggregate,holistic,reasoning,biggen_240612,kendall,random,5,4,0.9999999999999999,0.016666666666666666
|
| 437 |
-
aggregate,holistic,reasoning,biggen_240612,kendall,random,5,5,0.9999999999999999,0.016666666666666666
|
| 438 |
-
aggregate,holistic,reasoning,biggen_240612,kendall,random,5,6,0.9999999999999999,0.016666666666666666
|
| 439 |
-
aggregate,holistic,reasoning,biggen_240612,kendall,random,5,7,0.39999999999999997,0.48333333333333334
|
| 440 |
-
aggregate,holistic,reasoning,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 441 |
-
aggregate,holistic,reasoning,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 442 |
-
aggregate,holistic,refinement,biggen_240612,kendall,random,5,0,0.6,0.23333333333333334
|
| 443 |
-
aggregate,holistic,refinement,biggen_240612,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 444 |
-
aggregate,holistic,refinement,biggen_240612,kendall,random,5,2,0.19999999999999998,0.8166666666666667
|
| 445 |
-
aggregate,holistic,refinement,biggen_240612,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 446 |
-
aggregate,holistic,refinement,biggen_240612,kendall,random,5,4,0.6,0.23333333333333334
|
| 447 |
-
aggregate,holistic,refinement,biggen_240612,kendall,random,5,5,0.39999999999999997,0.48333333333333334
|
| 448 |
-
aggregate,holistic,refinement,biggen_240612,kendall,random,5,6,0.9999999999999999,0.016666666666666666
|
| 449 |
-
aggregate,holistic,refinement,biggen_240612,kendall,random,5,7,-0.19999999999999998,0.8166666666666667
|
| 450 |
-
aggregate,holistic,refinement,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 451 |
-
aggregate,holistic,refinement,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 452 |
-
aggregate,holistic,safety,biggen_240612,kendall,random,5,0,0.39999999999999997,0.48333333333333334
|
| 453 |
-
aggregate,holistic,safety,biggen_240612,kendall,random,5,1,0.19999999999999998,0.8166666666666667
|
| 454 |
-
aggregate,holistic,safety,biggen_240612,kendall,random,5,2,-0.6,0.23333333333333334
|
| 455 |
-
aggregate,holistic,safety,biggen_240612,kendall,random,5,3,0.0,1.0
|
| 456 |
-
aggregate,holistic,safety,biggen_240612,kendall,random,5,4,0.39999999999999997,0.48333333333333334
|
| 457 |
-
aggregate,holistic,safety,biggen_240612,kendall,random,5,5,0.0,1.0
|
| 458 |
-
aggregate,holistic,safety,biggen_240612,kendall,random,5,6,0.39999999999999997,0.48333333333333334
|
| 459 |
-
aggregate,holistic,safety,biggen_240612,kendall,random,5,7,-0.6,0.23333333333333334
|
| 460 |
-
aggregate,holistic,safety,biggen_240612,kendall,random,5,8,-0.19999999999999998,0.8166666666666667
|
| 461 |
-
aggregate,holistic,safety,biggen_240612,kendall,random,5,9,0.39999999999999997,0.48333333333333334
|
| 462 |
-
aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,0,0.6,0.23333333333333334
|
| 463 |
-
aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 464 |
-
aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,2,0.19999999999999998,0.8166666666666667
|
| 465 |
-
aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 466 |
-
aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,4,0.9999999999999999,0.016666666666666666
|
| 467 |
-
aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 468 |
-
aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,6,0.9999999999999999,0.016666666666666666
|
| 469 |
-
aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,7,-0.19999999999999998,0.8166666666666667
|
| 470 |
-
aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,8,0.9999999999999999,0.016666666666666666
|
| 471 |
-
aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 472 |
-
aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,0,0.6,0.23333333333333334
|
| 473 |
-
aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 474 |
-
aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,2,0.9999999999999999,0.016666666666666666
|
| 475 |
-
aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 476 |
-
aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,4,0.6,0.23333333333333334
|
| 477 |
-
aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,5,0.6,0.23333333333333334
|
| 478 |
-
aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 479 |
-
aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,7,0.0,1.0
|
| 480 |
-
aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 481 |
-
aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 482 |
-
aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,0,0.39999999999999997,0.48333333333333334
|
| 483 |
-
aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 484 |
-
aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,2,0.6,0.23333333333333334
|
| 485 |
-
aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,3,0.39999999999999997,0.48333333333333334
|
| 486 |
-
aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,4,0.6,0.23333333333333334
|
| 487 |
-
aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 488 |
-
aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,6,0.6,0.23333333333333334
|
| 489 |
-
aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 490 |
-
aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,8,0.6,0.23333333333333334
|
| 491 |
-
aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 492 |
-
aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,0,0.6,0.23333333333333334
|
| 493 |
-
aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,1,0.7378647873726218,0.07697417298126676
|
| 494 |
-
aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,2,0.6,0.23333333333333334
|
| 495 |
-
aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,3,0.5270462766947298,0.206507295485425
|
| 496 |
-
aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,4,0.7378647873726218,0.07697417298126676
|
| 497 |
-
aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,5,0.7378647873726218,0.07697417298126676
|
| 498 |
-
aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,6,0.7378647873726218,0.07697417298126676
|
| 499 |
-
aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 500 |
-
aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,8,0.7378647873726218,0.07697417298126676
|
| 501 |
-
aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,9,0.7378647873726218,0.07697417298126676
|
| 502 |
-
aggregate,holistic,coding_average,livebench_240701,kendall,random,5,0,0.39999999999999997,0.48333333333333334
|
| 503 |
-
aggregate,holistic,coding_average,livebench_240701,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 504 |
-
aggregate,holistic,coding_average,livebench_240701,kendall,random,5,2,0.6,0.23333333333333334
|
| 505 |
-
aggregate,holistic,coding_average,livebench_240701,kendall,random,5,3,0.31622776601683794,0.44848886103153174
|
| 506 |
-
aggregate,holistic,coding_average,livebench_240701,kendall,random,5,4,0.5270462766947298,0.206507295485425
|
| 507 |
-
aggregate,holistic,coding_average,livebench_240701,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 508 |
-
aggregate,holistic,coding_average,livebench_240701,kendall,random,5,6,0.5270462766947298,0.206507295485425
|
| 509 |
-
aggregate,holistic,coding_average,livebench_240701,kendall,random,5,7,0.7378647873726218,0.07697417298126676
|
| 510 |
-
aggregate,holistic,coding_average,livebench_240701,kendall,random,5,8,0.5270462766947298,0.206507295485425
|
| 511 |
-
aggregate,holistic,coding_average,livebench_240701,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 512 |
-
aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,0,0.39999999999999997,0.48333333333333334
|
| 513 |
-
aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 514 |
-
aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,2,0.6,0.23333333333333334
|
| 515 |
-
aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,3,0.39999999999999997,0.48333333333333334
|
| 516 |
-
aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 517 |
-
aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,5,0.9999999999999999,0.016666666666666666
|
| 518 |
-
aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,6,0.6,0.23333333333333334
|
| 519 |
-
aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 520 |
-
aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 521 |
-
aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 522 |
-
aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,0,0.6,0.23333333333333334
|
| 523 |
-
aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 524 |
-
aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 525 |
-
aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,3,0.6,0.23333333333333334
|
| 526 |
-
aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 527 |
-
aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 528 |
-
aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,6,0.9999999999999999,0.016666666666666666
|
| 529 |
-
aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,7,0.9999999999999999,0.016666666666666666
|
| 530 |
-
aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 531 |
-
aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 532 |
-
aggregate,holistic,language_average,livebench_240701,kendall,random,5,0,0.6,0.23333333333333334
|
| 533 |
-
aggregate,holistic,language_average,livebench_240701,kendall,random,5,1,0.6,0.23333333333333334
|
| 534 |
-
aggregate,holistic,language_average,livebench_240701,kendall,random,5,2,0.6,0.23333333333333334
|
| 535 |
-
aggregate,holistic,language_average,livebench_240701,kendall,random,5,3,0.6,0.23333333333333334
|
| 536 |
-
aggregate,holistic,language_average,livebench_240701,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 537 |
-
aggregate,holistic,language_average,livebench_240701,kendall,random,5,5,0.6,0.23333333333333334
|
| 538 |
-
aggregate,holistic,language_average,livebench_240701,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 539 |
-
aggregate,holistic,language_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 540 |
-
aggregate,holistic,language_average,livebench_240701,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 541 |
-
aggregate,holistic,language_average,livebench_240701,kendall,random,5,9,0.6,0.23333333333333334
|
| 542 |
-
aggregate,holistic,if_average,livebench_240701,kendall,random,5,0,0.39999999999999997,0.48333333333333334
|
| 543 |
-
aggregate,holistic,if_average,livebench_240701,kendall,random,5,1,0.6,0.23333333333333334
|
| 544 |
-
aggregate,holistic,if_average,livebench_240701,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 545 |
-
aggregate,holistic,if_average,livebench_240701,kendall,random,5,3,0.0,1.0
|
| 546 |
-
aggregate,holistic,if_average,livebench_240701,kendall,random,5,4,0.0,1.0
|
| 547 |
-
aggregate,holistic,if_average,livebench_240701,kendall,random,5,5,0.6,0.23333333333333334
|
| 548 |
-
aggregate,holistic,if_average,livebench_240701,kendall,random,5,6,0.19999999999999998,0.8166666666666667
|
| 549 |
-
aggregate,holistic,if_average,livebench_240701,kendall,random,5,7,0.39999999999999997,0.48333333333333334
|
| 550 |
-
aggregate,holistic,if_average,livebench_240701,kendall,random,5,8,0.0,1.0
|
| 551 |
-
aggregate,holistic,if_average,livebench_240701,kendall,random,5,9,0.6,0.23333333333333334
|
| 552 |
-
aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,0,0.9999999999999999,0.016666666666666666
|
| 553 |
-
aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,1,0.39999999999999997,0.48333333333333334
|
| 554 |
-
aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 555 |
-
aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 556 |
-
aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 557 |
-
aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,5,0.6,0.23333333333333334
|
| 558 |
-
aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,6,0.9999999999999999,0.016666666666666666
|
| 559 |
-
aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 560 |
-
aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,8,0.9999999999999999,0.016666666666666666
|
| 561 |
-
aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,9,0.9486832980505138,0.02297740150320607
|
| 562 |
-
aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,0,0.7999999999999999,0.08333333333333333
|
| 563 |
-
aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 564 |
-
aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 565 |
-
aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 566 |
-
aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 567 |
-
aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,5,0.9999999999999999,0.016666666666666666
|
| 568 |
-
aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 569 |
-
aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,7,0.9999999999999999,0.016666666666666666
|
| 570 |
-
aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 571 |
-
aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 572 |
-
aggregate,holistic,agieval,BLZ_240312,kendall,random,5,0,0.5270462766947299,0.206507295485425
|
| 573 |
-
aggregate,holistic,agieval,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 574 |
-
aggregate,holistic,agieval,BLZ_240312,kendall,random,5,2,0.6,0.23333333333333334
|
| 575 |
-
aggregate,holistic,agieval,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 576 |
-
aggregate,holistic,agieval,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 577 |
-
aggregate,holistic,agieval,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 578 |
-
aggregate,holistic,agieval,BLZ_240312,kendall,random,5,6,0.9999999999999999,0.016666666666666666
|
| 579 |
-
aggregate,holistic,agieval,BLZ_240312,kendall,random,5,7,0.6,0.23333333333333334
|
| 580 |
-
aggregate,holistic,agieval,BLZ_240312,kendall,random,5,8,0.19999999999999998,0.8166666666666667
|
| 581 |
-
aggregate,holistic,agieval,BLZ_240312,kendall,random,5,9,0.6,0.23333333333333334
|
| 582 |
-
aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,0,0.5270462766947298,0.206507295485425
|
| 583 |
-
aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 584 |
-
aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,2,0.9999999999999999,0.016666666666666666
|
| 585 |
-
aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 586 |
-
aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 587 |
-
aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 588 |
-
aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 589 |
-
aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,7,0.9999999999999999,0.016666666666666666
|
| 590 |
-
aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,8,0.19999999999999998,0.8166666666666667
|
| 591 |
-
aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 592 |
-
aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,0,0.19999999999999998,0.8166666666666667
|
| 593 |
-
aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 594 |
-
aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,2,0.6,0.23333333333333334
|
| 595 |
-
aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 596 |
-
aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 597 |
-
aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,5,0.39999999999999997,0.48333333333333334
|
| 598 |
-
aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,6,0.19999999999999998,0.8166666666666667
|
| 599 |
-
aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,7,0.39999999999999997,0.48333333333333334
|
| 600 |
-
aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
|
| 601 |
-
aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 602 |
-
aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,0,0.6,0.23333333333333334
|
| 603 |
-
aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 604 |
-
aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 605 |
-
aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 606 |
-
aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 607 |
-
aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,5,0.9999999999999999,0.016666666666666666
|
| 608 |
-
aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 609 |
-
aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,7,0.9999999999999999,0.016666666666666666
|
| 610 |
-
aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
|
| 611 |
-
aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 612 |
-
aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,0,0.5270462766947299,0.206507295485425
|
| 613 |
-
aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,1,0.39999999999999997,0.48333333333333334
|
| 614 |
-
aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 615 |
-
aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,3,0.6,0.23333333333333334
|
| 616 |
-
aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
|
| 617 |
-
aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334
|
| 618 |
-
aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 619 |
-
aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,7,0.6,0.23333333333333334
|
| 620 |
-
aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,8,0.19999999999999998,0.8166666666666667
|
| 621 |
-
aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 622 |
-
aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,0,0.9999999999999999,0.016666666666666666
|
| 623 |
-
aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 624 |
-
aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,2,1.0,0.019176729141549043
|
| 625 |
-
aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 626 |
-
aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
|
| 627 |
-
aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,5,0.9999999999999999,0.016666666666666666
|
| 628 |
-
aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,6,0.9999999999999999,0.016666666666666666
|
| 629 |
-
aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,7,0.9999999999999999,0.016666666666666666
|
| 630 |
-
aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
|
| 631 |
-
aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 632 |
-
aggregate,holistic,bbh,BLZ_240312,kendall,random,5,0,0.39999999999999997,0.48333333333333334
|
| 633 |
-
aggregate,holistic,bbh,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 634 |
-
aggregate,holistic,bbh,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 635 |
-
aggregate,holistic,bbh,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 636 |
-
aggregate,holistic,bbh,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 637 |
-
aggregate,holistic,bbh,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 638 |
-
aggregate,holistic,bbh,BLZ_240312,kendall,random,5,6,0.9486832980505137,0.02297740150320607
|
| 639 |
-
aggregate,holistic,bbh,BLZ_240312,kendall,random,5,7,0.19999999999999998,0.8166666666666667
|
| 640 |
-
aggregate,holistic,bbh,BLZ_240312,kendall,random,5,8,0.0,1.0
|
| 641 |
-
aggregate,holistic,bbh,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 642 |
-
aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333
|
| 643 |
-
aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,1,0.6,0.23333333333333334
|
| 644 |
-
aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,2,0.6,0.23333333333333334
|
| 645 |
-
aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 646 |
-
aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 647 |
-
aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334
|
| 648 |
-
aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,6,0.6,0.23333333333333334
|
| 649 |
-
aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,7,0.5270462766947299,0.206507295485425
|
| 650 |
-
aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 651 |
-
aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,9,0.6,0.23333333333333334
|
| 652 |
-
aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,0,0.6,0.23333333333333334
|
| 653 |
-
aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,1,0.0,1.0
|
| 654 |
-
aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 655 |
-
aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 656 |
-
aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,4,0.6,0.23333333333333334
|
| 657 |
-
aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,5,0.7378647873726218,0.07697417298126676
|
| 658 |
-
aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,6,0.6,0.23333333333333334
|
| 659 |
-
aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,7,0.6,0.23333333333333334
|
| 660 |
-
aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
|
| 661 |
-
aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,9,0.39999999999999997,0.48333333333333334
|
| 662 |
-
aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,0,0.6,0.23333333333333334
|
| 663 |
-
aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 664 |
-
aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,2,0.19999999999999998,0.8166666666666667
|
| 665 |
-
aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 666 |
-
aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,4,0.6,0.23333333333333334
|
| 667 |
-
aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,5,0.39999999999999997,0.48333333333333334
|
| 668 |
-
aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,6,0.39999999999999997,0.48333333333333334
|
| 669 |
-
aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,7,0.6,0.23333333333333334
|
| 670 |
-
aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,8,0.0,1.0
|
| 671 |
-
aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,9,0.39999999999999997,0.48333333333333334
|
| 672 |
-
aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,0,0.8366600265340756,0.05220363534131463
|
| 673 |
-
aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 674 |
-
aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 675 |
-
aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,3,0.6,0.23333333333333334
|
| 676 |
-
aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,4,0.6,0.23333333333333334
|
| 677 |
-
aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,5,0.9999999999999999,0.016666666666666666
|
| 678 |
-
aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,6,0.7378647873726218,0.07697417298126676
|
| 679 |
-
aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,7,0.5270462766947298,0.206507295485425
|
| 680 |
-
aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,8,0.3333333333333333,0.4349833603383296
|
| 681 |
-
aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,9,0.39999999999999997,0.48333333333333334
|
| 682 |
-
aggregate,holistic,magi,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333
|
| 683 |
-
aggregate,holistic,magi,BLZ_240312,kendall,random,5,1,0.5270462766947299,0.206507295485425
|
| 684 |
-
aggregate,holistic,magi,BLZ_240312,kendall,random,5,2,0.6,0.23333333333333334
|
| 685 |
-
aggregate,holistic,magi,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 686 |
-
aggregate,holistic,magi,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 687 |
-
aggregate,holistic,magi,BLZ_240312,kendall,random,5,5,0.9999999999999999,0.016666666666666666
|
| 688 |
-
aggregate,holistic,magi,BLZ_240312,kendall,random,5,6,0.10540925533894596,0.8005421074231263
|
| 689 |
-
aggregate,holistic,magi,BLZ_240312,kendall,random,5,7,0.39999999999999997,0.48333333333333334
|
| 690 |
-
aggregate,holistic,magi,BLZ_240312,kendall,random,5,8,0.31622776601683794,0.44848886103153174
|
| 691 |
-
aggregate,holistic,magi,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 692 |
-
aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,0,0.39999999999999997,0.48333333333333334
|
| 693 |
-
aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 694 |
-
aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,2,0.19999999999999998,0.8166666666666667
|
| 695 |
-
aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 696 |
-
aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,4,0.39999999999999997,0.48333333333333334
|
| 697 |
-
aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334
|
| 698 |
-
aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,6,0.6,0.23333333333333334
|
| 699 |
-
aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,7,0.9999999999999999,0.016666666666666666
|
| 700 |
-
aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,8,0.6,0.23333333333333334
|
| 701 |
-
aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 702 |
-
aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333
|
| 703 |
-
aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 704 |
-
aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 705 |
-
aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 706 |
-
aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
|
| 707 |
-
aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 708 |
-
aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,6,0.9999999999999999,0.016666666666666666
|
| 709 |
-
aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,7,0.9999999999999999,0.016666666666666666
|
| 710 |
-
aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
|
| 711 |
-
aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 712 |
-
aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,0,0.6,0.23333333333333334
|
| 713 |
-
aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,1,0.39999999999999997,0.48333333333333334
|
| 714 |
-
aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,2,0.0,1.0
|
| 715 |
-
aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,3,0.6,0.23333333333333334
|
| 716 |
-
aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,4,0.39999999999999997,0.48333333333333334
|
| 717 |
-
aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 718 |
-
aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,6,0.39999999999999997,0.48333333333333334
|
| 719 |
-
aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,7,0.9999999999999999,0.016666666666666666
|
| 720 |
-
aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,8,0.6,0.23333333333333334
|
| 721 |
-
aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,9,0.6,0.23333333333333334
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
cache/agreements_cache_9aca1000dd25da3a044f5fd80fad0266.csv
DELETED
|
@@ -1,721 +0,0 @@
|
|
| 1 |
-
scenario,scenario_source,ref_scenario,ref_source,corr_type,model_select_strategy,model_subset_size_requested,exp_n,correlation,p_value
|
| 2 |
-
hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666
|
| 3 |
-
hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.39999999999999997,0.48333333333333334
|
| 4 |
-
hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 5 |
-
hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.39999999999999997,0.48333333333333334
|
| 6 |
-
hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 7 |
-
hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
|
| 8 |
-
hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.39999999999999997,0.48333333333333334
|
| 9 |
-
hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 10 |
-
hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
|
| 11 |
-
hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 12 |
-
humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
|
| 13 |
-
humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 14 |
-
humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 15 |
-
humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.39999999999999997,0.48333333333333334
|
| 16 |
-
humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
|
| 17 |
-
humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
|
| 18 |
-
humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
|
| 19 |
-
humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334
|
| 20 |
-
humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334
|
| 21 |
-
humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
|
| 22 |
-
mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
|
| 23 |
-
mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.39999999999999997,0.48333333333333334
|
| 24 |
-
mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
|
| 25 |
-
mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.10540925533894598,0.8005421074231263
|
| 26 |
-
mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.19999999999999998,0.8166666666666667
|
| 27 |
-
mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334
|
| 28 |
-
mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.10540925533894598,0.8005421074231263
|
| 29 |
-
mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.10540925533894598,0.8005421074231263
|
| 30 |
-
mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,8,-0.5270462766947298,0.206507295485425
|
| 31 |
-
mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,9,-0.39999999999999997,0.48333333333333334
|
| 32 |
-
winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
|
| 33 |
-
winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 34 |
-
winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 35 |
-
winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 36 |
-
winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 37 |
-
winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 38 |
-
winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.39999999999999997,0.48333333333333334
|
| 39 |
-
winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334
|
| 40 |
-
winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 41 |
-
winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 42 |
-
grounding,biggen_240612,aggregate,holistic,kendall,random,5,0,0.9486832980505137,0.02297740150320607
|
| 43 |
-
grounding,biggen_240612,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 44 |
-
grounding,biggen_240612,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
|
| 45 |
-
grounding,biggen_240612,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 46 |
-
grounding,biggen_240612,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
|
| 47 |
-
grounding,biggen_240612,aggregate,holistic,kendall,random,5,5,0.7378647873726218,0.07697417298126676
|
| 48 |
-
grounding,biggen_240612,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
|
| 49 |
-
grounding,biggen_240612,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
|
| 50 |
-
grounding,biggen_240612,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
|
| 51 |
-
grounding,biggen_240612,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 52 |
-
instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,0,0.9486832980505137,0.02297740150320607
|
| 53 |
-
instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 54 |
-
instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,2,0.19999999999999998,0.8166666666666667
|
| 55 |
-
instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
|
| 56 |
-
instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,4,0.9486832980505137,0.02297740150320607
|
| 57 |
-
instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,5,0.7378647873726218,0.07697417298126676
|
| 58 |
-
instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
|
| 59 |
-
instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 60 |
-
instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 61 |
-
instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 62 |
-
planning,biggen_240612,aggregate,holistic,kendall,random,5,0,0.0,1.0
|
| 63 |
-
planning,biggen_240612,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 64 |
-
planning,biggen_240612,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 65 |
-
planning,biggen_240612,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 66 |
-
planning,biggen_240612,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
|
| 67 |
-
planning,biggen_240612,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 68 |
-
planning,biggen_240612,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
|
| 69 |
-
planning,biggen_240612,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 70 |
-
planning,biggen_240612,aggregate,holistic,kendall,random,5,8,0.39999999999999997,0.48333333333333334
|
| 71 |
-
planning,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 72 |
-
reasoning,biggen_240612,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
|
| 73 |
-
reasoning,biggen_240612,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 74 |
-
reasoning,biggen_240612,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
|
| 75 |
-
reasoning,biggen_240612,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 76 |
-
reasoning,biggen_240612,aggregate,holistic,kendall,random,5,4,0.39999999999999997,0.48333333333333334
|
| 77 |
-
reasoning,biggen_240612,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
|
| 78 |
-
reasoning,biggen_240612,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 79 |
-
reasoning,biggen_240612,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334
|
| 80 |
-
reasoning,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 81 |
-
reasoning,biggen_240612,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
|
| 82 |
-
refinement,biggen_240612,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
|
| 83 |
-
refinement,biggen_240612,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 84 |
-
refinement,biggen_240612,aggregate,holistic,kendall,random,5,2,0.39999999999999997,0.48333333333333334
|
| 85 |
-
refinement,biggen_240612,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 86 |
-
refinement,biggen_240612,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
|
| 87 |
-
refinement,biggen_240612,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 88 |
-
refinement,biggen_240612,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 89 |
-
refinement,biggen_240612,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 90 |
-
refinement,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 91 |
-
refinement,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 92 |
-
safety,biggen_240612,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
|
| 93 |
-
safety,biggen_240612,aggregate,holistic,kendall,random,5,1,0.0,1.0
|
| 94 |
-
safety,biggen_240612,aggregate,holistic,kendall,random,5,2,-0.39999999999999997,0.48333333333333334
|
| 95 |
-
safety,biggen_240612,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
|
| 96 |
-
safety,biggen_240612,aggregate,holistic,kendall,random,5,4,-0.6,0.23333333333333334
|
| 97 |
-
safety,biggen_240612,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334
|
| 98 |
-
safety,biggen_240612,aggregate,holistic,kendall,random,5,6,-0.19999999999999998,0.8166666666666667
|
| 99 |
-
safety,biggen_240612,aggregate,holistic,kendall,random,5,7,-0.39999999999999997,0.48333333333333334
|
| 100 |
-
safety,biggen_240612,aggregate,holistic,kendall,random,5,8,-0.19999999999999998,0.8166666666666667
|
| 101 |
-
safety,biggen_240612,aggregate,holistic,kendall,random,5,9,0.0,1.0
|
| 102 |
-
theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
|
| 103 |
-
theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
|
| 104 |
-
theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,2,0.39999999999999997,0.48333333333333334
|
| 105 |
-
theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 106 |
-
theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,4,0.39999999999999997,0.48333333333333334
|
| 107 |
-
theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 108 |
-
theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
|
| 109 |
-
theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 110 |
-
theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 111 |
-
theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 112 |
-
tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,0,0.19999999999999998,0.8166666666666667
|
| 113 |
-
tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 114 |
-
tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 115 |
-
tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
|
| 116 |
-
tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
|
| 117 |
-
tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
|
| 118 |
-
tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 119 |
-
tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334
|
| 120 |
-
tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 121 |
-
tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 122 |
-
livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
|
| 123 |
-
livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 124 |
-
livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
|
| 125 |
-
livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.39999999999999997,0.48333333333333334
|
| 126 |
-
livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
|
| 127 |
-
livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 128 |
-
livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
|
| 129 |
-
livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 130 |
-
livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334
|
| 131 |
-
livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 132 |
-
reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.7378647873726218,0.07697417298126676
|
| 133 |
-
reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 134 |
-
reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.7378647873726218,0.07697417298126676
|
| 135 |
-
reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.5270462766947298,0.206507295485425
|
| 136 |
-
reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 137 |
-
reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 138 |
-
reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 139 |
-
reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 140 |
-
reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 141 |
-
reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 142 |
-
coding_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.5270462766947298,0.206507295485425
|
| 143 |
-
coding_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.7378647873726218,0.07697417298126676
|
| 144 |
-
coding_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.5270462766947298,0.206507295485425
|
| 145 |
-
coding_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.31622776601683794,0.44848886103153174
|
| 146 |
-
coding_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
|
| 147 |
-
coding_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.7378647873726218,0.07697417298126676
|
| 148 |
-
coding_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
|
| 149 |
-
coding_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 150 |
-
coding_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334
|
| 151 |
-
coding_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 152 |
-
mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
|
| 153 |
-
mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 154 |
-
mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 155 |
-
mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
|
| 156 |
-
mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
|
| 157 |
-
mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
|
| 158 |
-
mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
|
| 159 |
-
mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 160 |
-
mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334
|
| 161 |
-
mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 162 |
-
data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
|
| 163 |
-
data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 164 |
-
data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 165 |
-
data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
|
| 166 |
-
data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 167 |
-
data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 168 |
-
data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 169 |
-
data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 170 |
-
data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 171 |
-
data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 172 |
-
language_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
|
| 173 |
-
language_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
|
| 174 |
-
language_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
|
| 175 |
-
language_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
|
| 176 |
-
language_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 177 |
-
language_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
|
| 178 |
-
language_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
|
| 179 |
-
language_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334
|
| 180 |
-
language_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 181 |
-
language_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
|
| 182 |
-
if_average,livebench_240701,aggregate,holistic,kendall,random,5,0,-0.39999999999999997,0.48333333333333334
|
| 183 |
-
if_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.19999999999999998,0.8166666666666667
|
| 184 |
-
if_average,livebench_240701,aggregate,holistic,kendall,random,5,2,-0.19999999999999998,0.8166666666666667
|
| 185 |
-
if_average,livebench_240701,aggregate,holistic,kendall,random,5,3,-0.6,0.23333333333333334
|
| 186 |
-
if_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.19999999999999998,0.8166666666666667
|
| 187 |
-
if_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.19999999999999998,0.8166666666666667
|
| 188 |
-
if_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.0,1.0
|
| 189 |
-
if_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334
|
| 190 |
-
if_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.19999999999999998,0.8166666666666667
|
| 191 |
-
if_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
|
| 192 |
-
arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
|
| 193 |
-
arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 194 |
-
arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,2,0.9999999999999999,0.016666666666666666
|
| 195 |
-
arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 196 |
-
arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 197 |
-
arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334
|
| 198 |
-
arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 199 |
-
arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
|
| 200 |
-
arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
|
| 201 |
-
arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
|
| 202 |
-
mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
|
| 203 |
-
mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 204 |
-
mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 205 |
-
mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 206 |
-
mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 207 |
-
mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
|
| 208 |
-
mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
|
| 209 |
-
mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 210 |
-
mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 211 |
-
mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 212 |
-
agieval,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666
|
| 213 |
-
agieval,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 214 |
-
agieval,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.9999999999999999,0.016666666666666666
|
| 215 |
-
agieval,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 216 |
-
agieval,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
|
| 217 |
-
agieval,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 218 |
-
agieval,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
|
| 219 |
-
agieval,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 220 |
-
agieval,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
|
| 221 |
-
agieval,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 222 |
-
arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9486832980505137,0.02297740150320607
|
| 223 |
-
arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 224 |
-
arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.9999999999999999,0.016666666666666666
|
| 225 |
-
arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 226 |
-
arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
|
| 227 |
-
arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
|
| 228 |
-
arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 229 |
-
arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
|
| 230 |
-
arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
|
| 231 |
-
arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 232 |
-
alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
|
| 233 |
-
alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 234 |
-
alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.39999999999999997,0.48333333333333334
|
| 235 |
-
alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9486832980505137,0.02297740150320607
|
| 236 |
-
alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 237 |
-
alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
|
| 238 |
-
alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 239 |
-
alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334
|
| 240 |
-
alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 241 |
-
alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 242 |
-
alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666
|
| 243 |
-
alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 244 |
-
alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 245 |
-
alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 246 |
-
alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
|
| 247 |
-
alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 248 |
-
alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.19999999999999998,0.8166666666666667
|
| 249 |
-
alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 250 |
-
alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
|
| 251 |
-
alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 252 |
-
alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
|
| 253 |
-
alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
|
| 254 |
-
alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.9999999999999999,0.016666666666666666
|
| 255 |
-
alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
|
| 256 |
-
alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
|
| 257 |
-
alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 258 |
-
alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
|
| 259 |
-
alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 260 |
-
alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
|
| 261 |
-
alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 262 |
-
arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9486832980505137,0.02297740150320607
|
| 263 |
-
arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
|
| 264 |
-
arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 265 |
-
arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 266 |
-
arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 267 |
-
arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
|
| 268 |
-
arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 269 |
-
arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334
|
| 270 |
-
arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 271 |
-
arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 272 |
-
bbh,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
|
| 273 |
-
bbh,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 274 |
-
bbh,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 275 |
-
bbh,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 276 |
-
bbh,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 277 |
-
bbh,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 278 |
-
bbh,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 279 |
-
bbh,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
|
| 280 |
-
bbh,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 281 |
-
bbh,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 282 |
-
eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
|
| 283 |
-
eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 284 |
-
eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 285 |
-
eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 286 |
-
eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
|
| 287 |
-
eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
|
| 288 |
-
eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 289 |
-
eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 290 |
-
eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 291 |
-
eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 292 |
-
gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
|
| 293 |
-
gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
|
| 294 |
-
gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.39999999999999997,0.48333333333333334
|
| 295 |
-
gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 296 |
-
gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
|
| 297 |
-
gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
|
| 298 |
-
gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 299 |
-
gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334
|
| 300 |
-
gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.39999999999999997,0.48333333333333334
|
| 301 |
-
gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 302 |
-
hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
|
| 303 |
-
hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 304 |
-
hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 305 |
-
hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 306 |
-
hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 307 |
-
hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 308 |
-
hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
|
| 309 |
-
hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.19999999999999998,0.8166666666666667
|
| 310 |
-
hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334
|
| 311 |
-
hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
|
| 312 |
-
llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666
|
| 313 |
-
llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9486832980505137,0.02297740150320607
|
| 314 |
-
llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.9999999999999999,0.016666666666666666
|
| 315 |
-
llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 316 |
-
llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9486832980505137,0.02297740150320607
|
| 317 |
-
llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 318 |
-
llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
|
| 319 |
-
llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 320 |
-
llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.7378647873726218,0.07697417298126676
|
| 321 |
-
llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 322 |
-
magi,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666
|
| 323 |
-
magi,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
|
| 324 |
-
magi,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
|
| 325 |
-
magi,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
|
| 326 |
-
magi,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
|
| 327 |
-
magi,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
|
| 328 |
-
magi,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 329 |
-
magi,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 330 |
-
magi,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.39999999999999997,0.48333333333333334
|
| 331 |
-
magi,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
|
| 332 |
-
mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
|
| 333 |
-
mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 334 |
-
mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.9999999999999999,0.016666666666666666
|
| 335 |
-
mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 336 |
-
mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 337 |
-
mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
|
| 338 |
-
mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
|
| 339 |
-
mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334
|
| 340 |
-
mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
|
| 341 |
-
mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 342 |
-
mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
|
| 343 |
-
mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 344 |
-
mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 345 |
-
mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 346 |
-
mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
|
| 347 |
-
mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334
|
| 348 |
-
mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
|
| 349 |
-
mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 350 |
-
mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 351 |
-
mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 352 |
-
biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
|
| 353 |
-
biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 354 |
-
biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 355 |
-
biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
|
| 356 |
-
biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
|
| 357 |
-
biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
|
| 358 |
-
biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 359 |
-
biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
|
| 360 |
-
biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 361 |
-
biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 362 |
-
aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,0,0.9999999999999999,0.016666666666666666
|
| 363 |
-
aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,1,0.39999999999999997,0.48333333333333334
|
| 364 |
-
aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 365 |
-
aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,3,0.39999999999999997,0.48333333333333334
|
| 366 |
-
aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 367 |
-
aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334
|
| 368 |
-
aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,6,0.39999999999999997,0.48333333333333334
|
| 369 |
-
aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 370 |
-
aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
|
| 371 |
-
aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 372 |
-
aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,0,0.39999999999999997,0.48333333333333334
|
| 373 |
-
aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 374 |
-
aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 375 |
-
aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,3,0.39999999999999997,0.48333333333333334
|
| 376 |
-
aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
|
| 377 |
-
aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334
|
| 378 |
-
aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,6,0.6,0.23333333333333334
|
| 379 |
-
aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,7,0.6,0.23333333333333334
|
| 380 |
-
aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,8,0.6,0.23333333333333334
|
| 381 |
-
aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,9,0.6,0.23333333333333334
|
| 382 |
-
aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,0,0.6,0.23333333333333334
|
| 383 |
-
aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,1,0.39999999999999997,0.48333333333333334
|
| 384 |
-
aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,2,0.6,0.23333333333333334
|
| 385 |
-
aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,3,0.10540925533894598,0.8005421074231263
|
| 386 |
-
aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,4,0.19999999999999998,0.8166666666666667
|
| 387 |
-
aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,5,0.39999999999999997,0.48333333333333334
|
| 388 |
-
aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,6,0.10540925533894598,0.8005421074231263
|
| 389 |
-
aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,7,0.10540925533894598,0.8005421074231263
|
| 390 |
-
aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,8,-0.5270462766947298,0.206507295485425
|
| 391 |
-
aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,9,-0.39999999999999997,0.48333333333333334
|
| 392 |
-
aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,0,0.6,0.23333333333333334
|
| 393 |
-
aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 394 |
-
aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 395 |
-
aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 396 |
-
aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 397 |
-
aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 398 |
-
aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,6,0.39999999999999997,0.48333333333333334
|
| 399 |
-
aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,7,0.39999999999999997,0.48333333333333334
|
| 400 |
-
aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 401 |
-
aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 402 |
-
aggregate,holistic,grounding,biggen_240612,kendall,random,5,0,0.9486832980505137,0.02297740150320607
|
| 403 |
-
aggregate,holistic,grounding,biggen_240612,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 404 |
-
aggregate,holistic,grounding,biggen_240612,kendall,random,5,2,0.6,0.23333333333333334
|
| 405 |
-
aggregate,holistic,grounding,biggen_240612,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 406 |
-
aggregate,holistic,grounding,biggen_240612,kendall,random,5,4,0.6,0.23333333333333334
|
| 407 |
-
aggregate,holistic,grounding,biggen_240612,kendall,random,5,5,0.7378647873726218,0.07697417298126676
|
| 408 |
-
aggregate,holistic,grounding,biggen_240612,kendall,random,5,6,0.6,0.23333333333333334
|
| 409 |
-
aggregate,holistic,grounding,biggen_240612,kendall,random,5,7,0.9999999999999999,0.016666666666666666
|
| 410 |
-
aggregate,holistic,grounding,biggen_240612,kendall,random,5,8,0.9999999999999999,0.016666666666666666
|
| 411 |
-
aggregate,holistic,grounding,biggen_240612,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 412 |
-
aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,0,0.9486832980505137,0.02297740150320607
|
| 413 |
-
aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 414 |
-
aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,2,0.19999999999999998,0.8166666666666667
|
| 415 |
-
aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,3,0.6,0.23333333333333334
|
| 416 |
-
aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,4,0.9486832980505137,0.02297740150320607
|
| 417 |
-
aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,5,0.7378647873726218,0.07697417298126676
|
| 418 |
-
aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,6,0.9999999999999999,0.016666666666666666
|
| 419 |
-
aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 420 |
-
aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 421 |
-
aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 422 |
-
aggregate,holistic,planning,biggen_240612,kendall,random,5,0,0.0,1.0
|
| 423 |
-
aggregate,holistic,planning,biggen_240612,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 424 |
-
aggregate,holistic,planning,biggen_240612,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 425 |
-
aggregate,holistic,planning,biggen_240612,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 426 |
-
aggregate,holistic,planning,biggen_240612,kendall,random,5,4,0.6,0.23333333333333334
|
| 427 |
-
aggregate,holistic,planning,biggen_240612,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 428 |
-
aggregate,holistic,planning,biggen_240612,kendall,random,5,6,0.6,0.23333333333333334
|
| 429 |
-
aggregate,holistic,planning,biggen_240612,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 430 |
-
aggregate,holistic,planning,biggen_240612,kendall,random,5,8,0.39999999999999997,0.48333333333333334
|
| 431 |
-
aggregate,holistic,planning,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 432 |
-
aggregate,holistic,reasoning,biggen_240612,kendall,random,5,0,0.7999999999999999,0.08333333333333333
|
| 433 |
-
aggregate,holistic,reasoning,biggen_240612,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 434 |
-
aggregate,holistic,reasoning,biggen_240612,kendall,random,5,2,0.6,0.23333333333333334
|
| 435 |
-
aggregate,holistic,reasoning,biggen_240612,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 436 |
-
aggregate,holistic,reasoning,biggen_240612,kendall,random,5,4,0.39999999999999997,0.48333333333333334
|
| 437 |
-
aggregate,holistic,reasoning,biggen_240612,kendall,random,5,5,0.9999999999999999,0.016666666666666666
|
| 438 |
-
aggregate,holistic,reasoning,biggen_240612,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 439 |
-
aggregate,holistic,reasoning,biggen_240612,kendall,random,5,7,0.6,0.23333333333333334
|
| 440 |
-
aggregate,holistic,reasoning,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 441 |
-
aggregate,holistic,reasoning,biggen_240612,kendall,random,5,9,0.6,0.23333333333333334
|
| 442 |
-
aggregate,holistic,refinement,biggen_240612,kendall,random,5,0,0.39999999999999997,0.48333333333333334
|
| 443 |
-
aggregate,holistic,refinement,biggen_240612,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 444 |
-
aggregate,holistic,refinement,biggen_240612,kendall,random,5,2,0.39999999999999997,0.48333333333333334
|
| 445 |
-
aggregate,holistic,refinement,biggen_240612,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 446 |
-
aggregate,holistic,refinement,biggen_240612,kendall,random,5,4,0.6,0.23333333333333334
|
| 447 |
-
aggregate,holistic,refinement,biggen_240612,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 448 |
-
aggregate,holistic,refinement,biggen_240612,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 449 |
-
aggregate,holistic,refinement,biggen_240612,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 450 |
-
aggregate,holistic,refinement,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 451 |
-
aggregate,holistic,refinement,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 452 |
-
aggregate,holistic,safety,biggen_240612,kendall,random,5,0,0.6,0.23333333333333334
|
| 453 |
-
aggregate,holistic,safety,biggen_240612,kendall,random,5,1,0.0,1.0
|
| 454 |
-
aggregate,holistic,safety,biggen_240612,kendall,random,5,2,-0.39999999999999997,0.48333333333333334
|
| 455 |
-
aggregate,holistic,safety,biggen_240612,kendall,random,5,3,0.6,0.23333333333333334
|
| 456 |
-
aggregate,holistic,safety,biggen_240612,kendall,random,5,4,-0.6,0.23333333333333334
|
| 457 |
-
aggregate,holistic,safety,biggen_240612,kendall,random,5,5,0.39999999999999997,0.48333333333333334
|
| 458 |
-
aggregate,holistic,safety,biggen_240612,kendall,random,5,6,-0.19999999999999998,0.8166666666666667
|
| 459 |
-
aggregate,holistic,safety,biggen_240612,kendall,random,5,7,-0.39999999999999997,0.48333333333333334
|
| 460 |
-
aggregate,holistic,safety,biggen_240612,kendall,random,5,8,-0.19999999999999998,0.8166666666666667
|
| 461 |
-
aggregate,holistic,safety,biggen_240612,kendall,random,5,9,0.0,1.0
|
| 462 |
-
aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,0,0.7999999999999999,0.08333333333333333
|
| 463 |
-
aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,1,0.6,0.23333333333333334
|
| 464 |
-
aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,2,0.39999999999999997,0.48333333333333334
|
| 465 |
-
aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 466 |
-
aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,4,0.39999999999999997,0.48333333333333334
|
| 467 |
-
aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 468 |
-
aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,6,0.9999999999999999,0.016666666666666666
|
| 469 |
-
aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 470 |
-
aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 471 |
-
aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 472 |
-
aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,0,0.19999999999999998,0.8166666666666667
|
| 473 |
-
aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 474 |
-
aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 475 |
-
aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,3,0.6,0.23333333333333334
|
| 476 |
-
aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,4,0.9999999999999999,0.016666666666666666
|
| 477 |
-
aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,5,0.6,0.23333333333333334
|
| 478 |
-
aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 479 |
-
aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,7,0.6,0.23333333333333334
|
| 480 |
-
aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 481 |
-
aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 482 |
-
aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,0,0.6,0.23333333333333334
|
| 483 |
-
aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 484 |
-
aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,2,0.6,0.23333333333333334
|
| 485 |
-
aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,3,0.39999999999999997,0.48333333333333334
|
| 486 |
-
aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,4,0.6,0.23333333333333334
|
| 487 |
-
aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 488 |
-
aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,6,0.6,0.23333333333333334
|
| 489 |
-
aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 490 |
-
aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,8,0.6,0.23333333333333334
|
| 491 |
-
aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 492 |
-
aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,0,0.7378647873726218,0.07697417298126676
|
| 493 |
-
aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 494 |
-
aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,2,0.7378647873726218,0.07697417298126676
|
| 495 |
-
aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,3,0.5270462766947298,0.206507295485425
|
| 496 |
-
aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 497 |
-
aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 498 |
-
aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 499 |
-
aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 500 |
-
aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 501 |
-
aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 502 |
-
aggregate,holistic,coding_average,livebench_240701,kendall,random,5,0,0.5270462766947298,0.206507295485425
|
| 503 |
-
aggregate,holistic,coding_average,livebench_240701,kendall,random,5,1,0.7378647873726218,0.07697417298126676
|
| 504 |
-
aggregate,holistic,coding_average,livebench_240701,kendall,random,5,2,0.5270462766947298,0.206507295485425
|
| 505 |
-
aggregate,holistic,coding_average,livebench_240701,kendall,random,5,3,0.31622776601683794,0.44848886103153174
|
| 506 |
-
aggregate,holistic,coding_average,livebench_240701,kendall,random,5,4,0.6,0.23333333333333334
|
| 507 |
-
aggregate,holistic,coding_average,livebench_240701,kendall,random,5,5,0.7378647873726218,0.07697417298126676
|
| 508 |
-
aggregate,holistic,coding_average,livebench_240701,kendall,random,5,6,0.6,0.23333333333333334
|
| 509 |
-
aggregate,holistic,coding_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 510 |
-
aggregate,holistic,coding_average,livebench_240701,kendall,random,5,8,0.6,0.23333333333333334
|
| 511 |
-
aggregate,holistic,coding_average,livebench_240701,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 512 |
-
aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,0,0.6,0.23333333333333334
|
| 513 |
-
aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 514 |
-
aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 515 |
-
aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,3,0.6,0.23333333333333334
|
| 516 |
-
aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,4,0.6,0.23333333333333334
|
| 517 |
-
aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,5,0.9999999999999999,0.016666666666666666
|
| 518 |
-
aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,6,0.6,0.23333333333333334
|
| 519 |
-
aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 520 |
-
aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,8,0.6,0.23333333333333334
|
| 521 |
-
aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 522 |
-
aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,0,0.7999999999999999,0.08333333333333333
|
| 523 |
-
aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 524 |
-
aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 525 |
-
aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,3,0.6,0.23333333333333334
|
| 526 |
-
aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 527 |
-
aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 528 |
-
aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 529 |
-
aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 530 |
-
aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 531 |
-
aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 532 |
-
aggregate,holistic,language_average,livebench_240701,kendall,random,5,0,0.7999999999999999,0.08333333333333333
|
| 533 |
-
aggregate,holistic,language_average,livebench_240701,kendall,random,5,1,0.6,0.23333333333333334
|
| 534 |
-
aggregate,holistic,language_average,livebench_240701,kendall,random,5,2,0.6,0.23333333333333334
|
| 535 |
-
aggregate,holistic,language_average,livebench_240701,kendall,random,5,3,0.6,0.23333333333333334
|
| 536 |
-
aggregate,holistic,language_average,livebench_240701,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 537 |
-
aggregate,holistic,language_average,livebench_240701,kendall,random,5,5,0.6,0.23333333333333334
|
| 538 |
-
aggregate,holistic,language_average,livebench_240701,kendall,random,5,6,0.6,0.23333333333333334
|
| 539 |
-
aggregate,holistic,language_average,livebench_240701,kendall,random,5,7,0.6,0.23333333333333334
|
| 540 |
-
aggregate,holistic,language_average,livebench_240701,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 541 |
-
aggregate,holistic,language_average,livebench_240701,kendall,random,5,9,0.6,0.23333333333333334
|
| 542 |
-
aggregate,holistic,if_average,livebench_240701,kendall,random,5,0,-0.39999999999999997,0.48333333333333334
|
| 543 |
-
aggregate,holistic,if_average,livebench_240701,kendall,random,5,1,0.19999999999999998,0.8166666666666667
|
| 544 |
-
aggregate,holistic,if_average,livebench_240701,kendall,random,5,2,-0.19999999999999998,0.8166666666666667
|
| 545 |
-
aggregate,holistic,if_average,livebench_240701,kendall,random,5,3,-0.6,0.23333333333333334
|
| 546 |
-
aggregate,holistic,if_average,livebench_240701,kendall,random,5,4,0.19999999999999998,0.8166666666666667
|
| 547 |
-
aggregate,holistic,if_average,livebench_240701,kendall,random,5,5,0.19999999999999998,0.8166666666666667
|
| 548 |
-
aggregate,holistic,if_average,livebench_240701,kendall,random,5,6,0.0,1.0
|
| 549 |
-
aggregate,holistic,if_average,livebench_240701,kendall,random,5,7,0.39999999999999997,0.48333333333333334
|
| 550 |
-
aggregate,holistic,if_average,livebench_240701,kendall,random,5,8,0.19999999999999998,0.8166666666666667
|
| 551 |
-
aggregate,holistic,if_average,livebench_240701,kendall,random,5,9,0.6,0.23333333333333334
|
| 552 |
-
aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,0,0.39999999999999997,0.48333333333333334
|
| 553 |
-
aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 554 |
-
aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,2,0.9999999999999999,0.016666666666666666
|
| 555 |
-
aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 556 |
-
aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 557 |
-
aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,5,0.39999999999999997,0.48333333333333334
|
| 558 |
-
aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 559 |
-
aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,7,0.9999999999999999,0.016666666666666666
|
| 560 |
-
aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,8,0.9999999999999999,0.016666666666666666
|
| 561 |
-
aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,9,0.6,0.23333333333333334
|
| 562 |
-
aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,0,0.7999999999999999,0.08333333333333333
|
| 563 |
-
aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 564 |
-
aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 565 |
-
aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 566 |
-
aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 567 |
-
aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,5,0.9999999999999999,0.016666666666666666
|
| 568 |
-
aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,6,0.9999999999999999,0.016666666666666666
|
| 569 |
-
aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 570 |
-
aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 571 |
-
aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 572 |
-
aggregate,holistic,agieval,BLZ_240312,kendall,random,5,0,0.9999999999999999,0.016666666666666666
|
| 573 |
-
aggregate,holistic,agieval,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 574 |
-
aggregate,holistic,agieval,BLZ_240312,kendall,random,5,2,0.9999999999999999,0.016666666666666666
|
| 575 |
-
aggregate,holistic,agieval,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 576 |
-
aggregate,holistic,agieval,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
|
| 577 |
-
aggregate,holistic,agieval,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 578 |
-
aggregate,holistic,agieval,BLZ_240312,kendall,random,5,6,0.9999999999999999,0.016666666666666666
|
| 579 |
-
aggregate,holistic,agieval,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 580 |
-
aggregate,holistic,agieval,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
|
| 581 |
-
aggregate,holistic,agieval,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 582 |
-
aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,0,0.9486832980505137,0.02297740150320607
|
| 583 |
-
aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 584 |
-
aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,2,0.9999999999999999,0.016666666666666666
|
| 585 |
-
aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 586 |
-
aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
|
| 587 |
-
aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334
|
| 588 |
-
aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 589 |
-
aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,7,0.9999999999999999,0.016666666666666666
|
| 590 |
-
aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
|
| 591 |
-
aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 592 |
-
aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333
|
| 593 |
-
aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 594 |
-
aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,2,0.39999999999999997,0.48333333333333334
|
| 595 |
-
aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,3,0.9486832980505137,0.02297740150320607
|
| 596 |
-
aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 597 |
-
aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334
|
| 598 |
-
aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 599 |
-
aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,7,0.39999999999999997,0.48333333333333334
|
| 600 |
-
aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 601 |
-
aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 602 |
-
aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,0,0.9999999999999999,0.016666666666666666
|
| 603 |
-
aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 604 |
-
aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 605 |
-
aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 606 |
-
aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,4,0.6,0.23333333333333334
|
| 607 |
-
aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 608 |
-
aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,6,0.19999999999999998,0.8166666666666667
|
| 609 |
-
aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 610 |
-
aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
|
| 611 |
-
aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 612 |
-
aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,0,0.39999999999999997,0.48333333333333334
|
| 613 |
-
aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,1,0.6,0.23333333333333334
|
| 614 |
-
aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,2,0.9999999999999999,0.016666666666666666
|
| 615 |
-
aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,3,0.6,0.23333333333333334
|
| 616 |
-
aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
|
| 617 |
-
aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 618 |
-
aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,6,0.6,0.23333333333333334
|
| 619 |
-
aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 620 |
-
aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
|
| 621 |
-
aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 622 |
-
aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,0,0.9486832980505137,0.02297740150320607
|
| 623 |
-
aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,1,0.6,0.23333333333333334
|
| 624 |
-
aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 625 |
-
aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 626 |
-
aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 627 |
-
aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334
|
| 628 |
-
aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 629 |
-
aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,7,0.6,0.23333333333333334
|
| 630 |
-
aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 631 |
-
aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 632 |
-
aggregate,holistic,bbh,BLZ_240312,kendall,random,5,0,0.6,0.23333333333333334
|
| 633 |
-
aggregate,holistic,bbh,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 634 |
-
aggregate,holistic,bbh,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 635 |
-
aggregate,holistic,bbh,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 636 |
-
aggregate,holistic,bbh,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 637 |
-
aggregate,holistic,bbh,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 638 |
-
aggregate,holistic,bbh,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 639 |
-
aggregate,holistic,bbh,BLZ_240312,kendall,random,5,7,0.9999999999999999,0.016666666666666666
|
| 640 |
-
aggregate,holistic,bbh,BLZ_240312,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 641 |
-
aggregate,holistic,bbh,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 642 |
-
aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333
|
| 643 |
-
aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 644 |
-
aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 645 |
-
aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 646 |
-
aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
|
| 647 |
-
aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334
|
| 648 |
-
aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 649 |
-
aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 650 |
-
aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 651 |
-
aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 652 |
-
aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333
|
| 653 |
-
aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,1,0.6,0.23333333333333334
|
| 654 |
-
aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,2,0.39999999999999997,0.48333333333333334
|
| 655 |
-
aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 656 |
-
aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
|
| 657 |
-
aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,5,0.9999999999999999,0.016666666666666666
|
| 658 |
-
aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 659 |
-
aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,7,0.6,0.23333333333333334
|
| 660 |
-
aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,8,0.39999999999999997,0.48333333333333334
|
| 661 |
-
aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 662 |
-
aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333
|
| 663 |
-
aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 664 |
-
aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 665 |
-
aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 666 |
-
aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 667 |
-
aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 668 |
-
aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,6,0.6,0.23333333333333334
|
| 669 |
-
aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,7,0.19999999999999998,0.8166666666666667
|
| 670 |
-
aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,8,0.6,0.23333333333333334
|
| 671 |
-
aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,9,0.6,0.23333333333333334
|
| 672 |
-
aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,0,0.9999999999999999,0.016666666666666666
|
| 673 |
-
aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,1,0.9486832980505137,0.02297740150320607
|
| 674 |
-
aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,2,0.9999999999999999,0.016666666666666666
|
| 675 |
-
aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 676 |
-
aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,4,0.9486832980505137,0.02297740150320607
|
| 677 |
-
aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
|
| 678 |
-
aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,6,0.6,0.23333333333333334
|
| 679 |
-
aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 680 |
-
aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,8,0.7378647873726218,0.07697417298126676
|
| 681 |
-
aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
| 682 |
-
aggregate,holistic,magi,BLZ_240312,kendall,random,5,0,0.9999999999999999,0.016666666666666666
|
| 683 |
-
aggregate,holistic,magi,BLZ_240312,kendall,random,5,1,0.6,0.23333333333333334
|
| 684 |
-
aggregate,holistic,magi,BLZ_240312,kendall,random,5,2,0.6,0.23333333333333334
|
| 685 |
-
aggregate,holistic,magi,BLZ_240312,kendall,random,5,3,0.6,0.23333333333333334
|
| 686 |
-
aggregate,holistic,magi,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
|
| 687 |
-
aggregate,holistic,magi,BLZ_240312,kendall,random,5,5,0.9999999999999999,0.016666666666666666
|
| 688 |
-
aggregate,holistic,magi,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 689 |
-
aggregate,holistic,magi,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 690 |
-
aggregate,holistic,magi,BLZ_240312,kendall,random,5,8,0.39999999999999997,0.48333333333333334
|
| 691 |
-
aggregate,holistic,magi,BLZ_240312,kendall,random,5,9,0.6,0.23333333333333334
|
| 692 |
-
aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333
|
| 693 |
-
aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 694 |
-
aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,2,0.9999999999999999,0.016666666666666666
|
| 695 |
-
aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333
|
| 696 |
-
aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
|
| 697 |
-
aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334
|
| 698 |
-
aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,6,0.9999999999999999,0.016666666666666666
|
| 699 |
-
aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,7,0.6,0.23333333333333334
|
| 700 |
-
aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
|
| 701 |
-
aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 702 |
-
aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333
|
| 703 |
-
aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333
|
| 704 |
-
aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 705 |
-
aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
|
| 706 |
-
aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
|
| 707 |
-
aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,5,0.39999999999999997,0.48333333333333334
|
| 708 |
-
aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,6,0.9999999999999999,0.016666666666666666
|
| 709 |
-
aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333
|
| 710 |
-
aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 711 |
-
aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
|
| 712 |
-
aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,0,0.6,0.23333333333333334
|
| 713 |
-
aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,1,0.9999999999999999,0.016666666666666666
|
| 714 |
-
aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,2,0.7999999999999999,0.08333333333333333
|
| 715 |
-
aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,3,0.6,0.23333333333333334
|
| 716 |
-
aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,4,0.9999999999999999,0.016666666666666666
|
| 717 |
-
aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,5,0.6,0.23333333333333334
|
| 718 |
-
aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,6,0.7999999999999999,0.08333333333333333
|
| 719 |
-
aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,7,0.9999999999999999,0.016666666666666666
|
| 720 |
-
aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333
|
| 721 |
-
aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,9,0.7999999999999999,0.08333333333333333
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
cache/agreements_cache_a8b645e4d5ba862fbfa9ef3ecf73b44c.csv
DELETED
|
@@ -1,721 +0,0 @@
|
|
| 1 |
-
scenario,scenario_source,ref_scenario,ref_source,corr_type,model_select_strategy,model_subset_size_requested,exp_n,correlation,p_value
|
| 2 |
-
hellaswag,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.0,1.0
|
| 3 |
-
hellaswag,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
|
| 4 |
-
hellaswag,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,-0.19999999999999998,0.8166666666666667
|
| 5 |
-
hellaswag,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.6,0.23333333333333334
|
| 6 |
-
hellaswag,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.39999999999999997,0.48333333333333334
|
| 7 |
-
hellaswag,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.19999999999999998,0.8166666666666667
|
| 8 |
-
hellaswag,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
|
| 9 |
-
hellaswag,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
|
| 10 |
-
hellaswag,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.39999999999999997,0.48333333333333334
|
| 11 |
-
hellaswag,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.6,0.23333333333333334
|
| 12 |
-
humaneval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,-0.39999999999999997,0.48333333333333334
|
| 13 |
-
humaneval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,-0.5270462766947298,0.206507295485425
|
| 14 |
-
humaneval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.5270462766947298,0.206507295485425
|
| 15 |
-
humaneval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.5270462766947298,0.206507295485425
|
| 16 |
-
humaneval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,-0.22360679774997896,0.6015081344405899
|
| 17 |
-
humaneval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.10540925533894598,0.8005421074231263
|
| 18 |
-
humaneval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,-0.10540925533894598,0.8005421074231263
|
| 19 |
-
humaneval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.39999999999999997,0.48333333333333334
|
| 20 |
-
humaneval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,-0.10540925533894598,0.8005421074231263
|
| 21 |
-
humaneval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,-0.22360679774997896,0.6015081344405899
|
| 22 |
-
mbpp,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.10540925533894598,0.8005421074231263
|
| 23 |
-
mbpp,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,-0.31622776601683794,0.44848886103153174
|
| 24 |
-
mbpp,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,-0.31622776601683794,0.44848886103153174
|
| 25 |
-
mbpp,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.10540925533894598,0.8005421074231263
|
| 26 |
-
mbpp,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,-0.39999999999999997,0.48333333333333334
|
| 27 |
-
mbpp,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.10540925533894598,0.8005421074231263
|
| 28 |
-
mbpp,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
|
| 29 |
-
mbpp,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.39999999999999997,0.48333333333333334
|
| 30 |
-
mbpp,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.10540925533894598,0.8005421074231263
|
| 31 |
-
mbpp,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.39999999999999997,0.48333333333333334
|
| 32 |
-
winogrande,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,-0.19999999999999998,0.8166666666666667
|
| 33 |
-
winogrande,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.7999999999999999,0.08333333333333333
|
| 34 |
-
winogrande,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.0,1.0
|
| 35 |
-
winogrande,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,-0.19999999999999998,0.8166666666666667
|
| 36 |
-
winogrande,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.31622776601683794,0.44848886103153174
|
| 37 |
-
winogrande,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.7999999999999999,0.08333333333333333
|
| 38 |
-
winogrande,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,-0.9999999999999999,0.016666666666666666
|
| 39 |
-
winogrande,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.7999999999999999,0.08333333333333333
|
| 40 |
-
winogrande,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.0,1.0
|
| 41 |
-
winogrande,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,-0.19999999999999998,0.8166666666666667
|
| 42 |
-
grounding,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.9486832980505137,0.02297740150320607
|
| 43 |
-
grounding,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.19999999999999998,0.8166666666666667
|
| 44 |
-
grounding,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.10540925533894598,0.8005421074231263
|
| 45 |
-
grounding,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.31622776601683794,0.44848886103153174
|
| 46 |
-
grounding,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.9486832980505137,0.02297740150320607
|
| 47 |
-
grounding,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.9486832980505137,0.02297740150320607
|
| 48 |
-
grounding,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.31622776601683794,0.44848886103153174
|
| 49 |
-
grounding,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.19999999999999998,0.8166666666666667
|
| 50 |
-
grounding,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.39999999999999997,0.48333333333333334
|
| 51 |
-
grounding,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.19999999999999998,0.8166666666666667
|
| 52 |
-
instruction_following,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.0,1.0
|
| 53 |
-
instruction_following,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
|
| 54 |
-
instruction_following,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.7378647873726218,0.07697417298126676
|
| 55 |
-
instruction_following,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,3,-0.39999999999999997,0.48333333333333334
|
| 56 |
-
instruction_following,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.8944271909999159,0.0367138563627041
|
| 57 |
-
instruction_following,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.9486832980505137,0.02297740150320607
|
| 58 |
-
instruction_following,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.9486832980505137,0.02297740150320607
|
| 59 |
-
instruction_following,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.0,1.0
|
| 60 |
-
instruction_following,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.8944271909999159,0.0367138563627041
|
| 61 |
-
instruction_following,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.7378647873726218,0.07697417298126676
|
| 62 |
-
planning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.7378647873726218,0.07697417298126676
|
| 63 |
-
planning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.7999999999999999,0.08333333333333333
|
| 64 |
-
planning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.39999999999999997,0.48333333333333334
|
| 65 |
-
planning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.39999999999999997,0.48333333333333334
|
| 66 |
-
planning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.19999999999999998,0.8166666666666667
|
| 67 |
-
planning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.39999999999999997,0.48333333333333334
|
| 68 |
-
planning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
|
| 69 |
-
planning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.7378647873726218,0.07697417298126676
|
| 70 |
-
planning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,8,-0.10540925533894598,0.8005421074231263
|
| 71 |
-
planning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.7378647873726218,0.07697417298126676
|
| 72 |
-
reasoning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.7378647873726218,0.07697417298126676
|
| 73 |
-
reasoning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.6,0.23333333333333334
|
| 74 |
-
reasoning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.7378647873726218,0.07697417298126676
|
| 75 |
-
reasoning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.6,0.23333333333333334
|
| 76 |
-
reasoning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.5270462766947298,0.206507295485425
|
| 77 |
-
reasoning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.7999999999999999,0.08333333333333333
|
| 78 |
-
reasoning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.5270462766947298,0.206507295485425
|
| 79 |
-
reasoning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
|
| 80 |
-
reasoning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.0,1.0
|
| 81 |
-
reasoning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.39999999999999997,0.48333333333333334
|
| 82 |
-
refinement,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.6,0.23333333333333334
|
| 83 |
-
refinement,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
|
| 84 |
-
refinement,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.19999999999999998,0.8166666666666667
|
| 85 |
-
refinement,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.39999999999999997,0.48333333333333334
|
| 86 |
-
refinement,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.39999999999999997,0.48333333333333334
|
| 87 |
-
refinement,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.39999999999999997,0.48333333333333334
|
| 88 |
-
refinement,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
|
| 89 |
-
refinement,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.39999999999999997,0.48333333333333334
|
| 90 |
-
refinement,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.39999999999999997,0.48333333333333334
|
| 91 |
-
refinement,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.6,0.23333333333333334
|
| 92 |
-
safety,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.0,1.0
|
| 93 |
-
safety,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.0,1.0
|
| 94 |
-
safety,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,2,-0.19999999999999998,0.8166666666666667
|
| 95 |
-
safety,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.0,1.0
|
| 96 |
-
safety,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,4,-0.19999999999999998,0.8166666666666667
|
| 97 |
-
safety,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,5,-0.6,0.23333333333333334
|
| 98 |
-
safety,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.7999999999999999,0.08333333333333333
|
| 99 |
-
safety,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,7,-0.6,0.23333333333333334
|
| 100 |
-
safety,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.6,0.23333333333333334
|
| 101 |
-
safety,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.6,0.23333333333333334
|
| 102 |
-
theory_of_mind,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.19999999999999998,0.8166666666666667
|
| 103 |
-
theory_of_mind,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
|
| 104 |
-
theory_of_mind,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.6,0.23333333333333334
|
| 105 |
-
theory_of_mind,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.0,1.0
|
| 106 |
-
theory_of_mind,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.19999999999999998,0.8166666666666667
|
| 107 |
-
theory_of_mind,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.19999999999999998,0.8166666666666667
|
| 108 |
-
theory_of_mind,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
|
| 109 |
-
theory_of_mind,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.0,1.0
|
| 110 |
-
theory_of_mind,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.19999999999999998,0.8166666666666667
|
| 111 |
-
theory_of_mind,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.39999999999999997,0.48333333333333334
|
| 112 |
-
tool_usage,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.19999999999999998,0.8166666666666667
|
| 113 |
-
tool_usage,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
|
| 114 |
-
tool_usage,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.9999999999999999,0.016666666666666666
|
| 115 |
-
tool_usage,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.9999999999999999,0.016666666666666666
|
| 116 |
-
tool_usage,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.39999999999999997,0.48333333333333334
|
| 117 |
-
tool_usage,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.9999999999999999,0.016666666666666666
|
| 118 |
-
tool_usage,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.19999999999999998,0.8166666666666667
|
| 119 |
-
tool_usage,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
|
| 120 |
-
tool_usage,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.7999999999999999,0.08333333333333333
|
| 121 |
-
tool_usage,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.39999999999999997,0.48333333333333334
|
| 122 |
-
livebench_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.6,0.23333333333333334
|
| 123 |
-
livebench_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.7999999999999999,0.08333333333333333
|
| 124 |
-
livebench_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.7999999999999999,0.08333333333333333
|
| 125 |
-
livebench_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.6,0.23333333333333334
|
| 126 |
-
livebench_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.6,0.23333333333333334
|
| 127 |
-
livebench_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.39999999999999997,0.48333333333333334
|
| 128 |
-
livebench_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.6,0.23333333333333334
|
| 129 |
-
livebench_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.7999999999999999,0.08333333333333333
|
| 130 |
-
livebench_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.39999999999999997,0.48333333333333334
|
| 131 |
-
livebench_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.39999999999999997,0.48333333333333334
|
| 132 |
-
reasoning_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.7378647873726218,0.07697417298126676
|
| 133 |
-
reasoning_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.5270462766947298,0.206507295485425
|
| 134 |
-
reasoning_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.7378647873726218,0.07697417298126676
|
| 135 |
-
reasoning_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.7378647873726218,0.07697417298126676
|
| 136 |
-
reasoning_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.5270462766947298,0.206507295485425
|
| 137 |
-
reasoning_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.7999999999999999,0.08333333333333333
|
| 138 |
-
reasoning_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.7378647873726218,0.07697417298126676
|
| 139 |
-
reasoning_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.7999999999999999,0.08333333333333333
|
| 140 |
-
reasoning_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.5270462766947298,0.206507295485425
|
| 141 |
-
reasoning_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.7378647873726218,0.07697417298126676
|
| 142 |
-
coding_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.31622776601683794,0.44848886103153174
|
| 143 |
-
coding_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.31622776601683794,0.44848886103153174
|
| 144 |
-
coding_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.6,0.23333333333333334
|
| 145 |
-
coding_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.31622776601683794,0.44848886103153174
|
| 146 |
-
coding_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.31622776601683794,0.44848886103153174
|
| 147 |
-
coding_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.5270462766947298,0.206507295485425
|
| 148 |
-
coding_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.5270462766947298,0.206507295485425
|
| 149 |
-
coding_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.5270462766947298,0.206507295485425
|
| 150 |
-
coding_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.5270462766947298,0.206507295485425
|
| 151 |
-
coding_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.5270462766947298,0.206507295485425
|
| 152 |
-
mathematics_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.6,0.23333333333333334
|
| 153 |
-
mathematics_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.6,0.23333333333333334
|
| 154 |
-
mathematics_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.6,0.23333333333333334
|
| 155 |
-
mathematics_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.6,0.23333333333333334
|
| 156 |
-
mathematics_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.6,0.23333333333333334
|
| 157 |
-
mathematics_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.6,0.23333333333333334
|
| 158 |
-
mathematics_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.6,0.23333333333333334
|
| 159 |
-
mathematics_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
|
| 160 |
-
mathematics_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.6,0.23333333333333334
|
| 161 |
-
mathematics_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.6,0.23333333333333334
|
| 162 |
-
data_analysis_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.6,0.23333333333333334
|
| 163 |
-
data_analysis_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.6,0.23333333333333334
|
| 164 |
-
data_analysis_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.6,0.23333333333333334
|
| 165 |
-
data_analysis_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.6,0.23333333333333334
|
| 166 |
-
data_analysis_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.7999999999999999,0.08333333333333333
|
| 167 |
-
data_analysis_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.7999999999999999,0.08333333333333333
|
| 168 |
-
data_analysis_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.7999999999999999,0.08333333333333333
|
| 169 |
-
data_analysis_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
|
| 170 |
-
data_analysis_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.7999999999999999,0.08333333333333333
|
| 171 |
-
data_analysis_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.7999999999999999,0.08333333333333333
|
| 172 |
-
language_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.6,0.23333333333333334
|
| 173 |
-
language_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.7999999999999999,0.08333333333333333
|
| 174 |
-
language_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.7999999999999999,0.08333333333333333
|
| 175 |
-
language_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.7999999999999999,0.08333333333333333
|
| 176 |
-
language_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.7999999999999999,0.08333333333333333
|
| 177 |
-
language_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.7999999999999999,0.08333333333333333
|
| 178 |
-
language_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.6,0.23333333333333334
|
| 179 |
-
language_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
|
| 180 |
-
language_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.6,0.23333333333333334
|
| 181 |
-
language_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.6,0.23333333333333334
|
| 182 |
-
if_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.0,1.0
|
| 183 |
-
if_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,1,-0.6,0.23333333333333334
|
| 184 |
-
if_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.19999999999999998,0.8166666666666667
|
| 185 |
-
if_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.19999999999999998,0.8166666666666667
|
| 186 |
-
if_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.19999999999999998,0.8166666666666667
|
| 187 |
-
if_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.19999999999999998,0.8166666666666667
|
| 188 |
-
if_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.19999999999999998,0.8166666666666667
|
| 189 |
-
if_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.19999999999999998,0.8166666666666667
|
| 190 |
-
if_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.0,1.0
|
| 191 |
-
if_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.19999999999999998,0.8166666666666667
|
| 192 |
-
arena_hard,arena_hard_2404,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.39999999999999997,0.48333333333333334
|
| 193 |
-
arena_hard,arena_hard_2404,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.9999999999999999,0.016666666666666666
|
| 194 |
-
arena_hard,arena_hard_2404,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.19999999999999998,0.8166666666666667
|
| 195 |
-
arena_hard,arena_hard_2404,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.7999999999999999,0.08333333333333333
|
| 196 |
-
arena_hard,arena_hard_2404,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.9999999999999999,0.016666666666666666
|
| 197 |
-
arena_hard,arena_hard_2404,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.7999999999999999,0.08333333333333333
|
| 198 |
-
arena_hard,arena_hard_2404,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
|
| 199 |
-
arena_hard,arena_hard_2404,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.9999999999999999,0.016666666666666666
|
| 200 |
-
arena_hard,arena_hard_2404,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.7999999999999999,0.08333333333333333
|
| 201 |
-
arena_hard,arena_hard_2404,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.7999999999999999,0.08333333333333333
|
| 202 |
-
mixeval,mixeval_240601,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.7999999999999999,0.08333333333333333
|
| 203 |
-
mixeval,mixeval_240601,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.7999999999999999,0.08333333333333333
|
| 204 |
-
mixeval,mixeval_240601,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.7999999999999999,0.08333333333333333
|
| 205 |
-
mixeval,mixeval_240601,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.7999999999999999,0.08333333333333333
|
| 206 |
-
mixeval,mixeval_240601,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.7999999999999999,0.08333333333333333
|
| 207 |
-
mixeval,mixeval_240601,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.7999999999999999,0.08333333333333333
|
| 208 |
-
mixeval,mixeval_240601,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.7999999999999999,0.08333333333333333
|
| 209 |
-
mixeval,mixeval_240601,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.7999999999999999,0.08333333333333333
|
| 210 |
-
mixeval,mixeval_240601,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.7999999999999999,0.08333333333333333
|
| 211 |
-
mixeval,mixeval_240601,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.7999999999999999,0.08333333333333333
|
| 212 |
-
agieval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.31622776601683794,0.44848886103153174
|
| 213 |
-
agieval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.31622776601683794,0.44848886103153174
|
| 214 |
-
agieval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.39999999999999997,0.48333333333333334
|
| 215 |
-
agieval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.7999999999999999,0.08333333333333333
|
| 216 |
-
agieval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.7999999999999999,0.08333333333333333
|
| 217 |
-
agieval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.9999999999999999,0.016666666666666666
|
| 218 |
-
agieval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.19999999999999998,0.8166666666666667
|
| 219 |
-
agieval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.19999999999999998,0.8166666666666667
|
| 220 |
-
agieval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.39999999999999997,0.48333333333333334
|
| 221 |
-
agieval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.7999999999999999,0.08333333333333333
|
| 222 |
-
arc_c,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.6,0.23333333333333334
|
| 223 |
-
arc_c,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
|
| 224 |
-
arc_c,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,-0.19999999999999998,0.8166666666666667
|
| 225 |
-
arc_c,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,-0.39999999999999997,0.48333333333333334
|
| 226 |
-
arc_c,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.0,1.0
|
| 227 |
-
arc_c,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.6,0.23333333333333334
|
| 228 |
-
arc_c,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.31622776601683794,0.44848886103153174
|
| 229 |
-
arc_c,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
|
| 230 |
-
arc_c,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.39999999999999997,0.48333333333333334
|
| 231 |
-
arc_c,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.7378647873726218,0.07697417298126676
|
| 232 |
-
alpacav1,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,-0.31622776601683794,0.44848886103153174
|
| 233 |
-
alpacav1,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,-0.7999999999999999,0.08333333333333333
|
| 234 |
-
alpacav1,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.7999999999999999,0.08333333333333333
|
| 235 |
-
alpacav1,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.7999999999999999,0.08333333333333333
|
| 236 |
-
alpacav1,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.39999999999999997,0.48333333333333334
|
| 237 |
-
alpacav1,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.39999999999999997,0.48333333333333334
|
| 238 |
-
alpacav1,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.6,0.23333333333333334
|
| 239 |
-
alpacav1,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.7378647873726218,0.07697417298126676
|
| 240 |
-
alpacav1,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.6,0.23333333333333334
|
| 241 |
-
alpacav1,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.31622776601683794,0.44848886103153174
|
| 242 |
-
alpacav2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.39999999999999997,0.48333333333333334
|
| 243 |
-
alpacav2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.19999999999999998,0.8166666666666667
|
| 244 |
-
alpacav2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.39999999999999997,0.48333333333333334
|
| 245 |
-
alpacav2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.7378647873726218,0.07697417298126676
|
| 246 |
-
alpacav2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.39999999999999997,0.48333333333333334
|
| 247 |
-
alpacav2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,-0.6,0.23333333333333334
|
| 248 |
-
alpacav2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,-0.39999999999999997,0.48333333333333334
|
| 249 |
-
alpacav2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
|
| 250 |
-
alpacav2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.0,1.0
|
| 251 |
-
alpacav2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.6,0.23333333333333334
|
| 252 |
-
alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.0,1.0
|
| 253 |
-
alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,-0.6,0.23333333333333334
|
| 254 |
-
alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.7999999999999999,0.08333333333333333
|
| 255 |
-
alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.0,1.0
|
| 256 |
-
alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.6,0.23333333333333334
|
| 257 |
-
alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.39999999999999997,0.48333333333333334
|
| 258 |
-
alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
|
| 259 |
-
alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
|
| 260 |
-
alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,-0.39999999999999997,0.48333333333333334
|
| 261 |
-
alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.0,1.0
|
| 262 |
-
arena_elo,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.31622776601683794,0.44848886103153174
|
| 263 |
-
arena_elo,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.6,0.23333333333333334
|
| 264 |
-
arena_elo,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.31622776601683794,0.44848886103153174
|
| 265 |
-
arena_elo,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,-0.9999999999999999,0.016666666666666666
|
| 266 |
-
arena_elo,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.39999999999999997,0.48333333333333334
|
| 267 |
-
arena_elo,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.31622776601683794,0.44848886103153174
|
| 268 |
-
arena_elo,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,-0.9999999999999999,0.016666666666666666
|
| 269 |
-
arena_elo,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
|
| 270 |
-
arena_elo,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,-0.10540925533894598,0.8005421074231263
|
| 271 |
-
arena_elo,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.6,0.23333333333333334
|
| 272 |
-
bbh,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.9486832980505137,0.02297740150320607
|
| 273 |
-
bbh,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.31622776601683794,0.44848886103153174
|
| 274 |
-
bbh,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,-0.39999999999999997,0.48333333333333334
|
| 275 |
-
bbh,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.9999999999999999,0.016666666666666666
|
| 276 |
-
bbh,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.0,1.0
|
| 277 |
-
bbh,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,-0.39999999999999997,0.48333333333333334
|
| 278 |
-
bbh,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.7999999999999999,0.08333333333333333
|
| 279 |
-
bbh,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.7999999999999999,0.08333333333333333
|
| 280 |
-
bbh,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.5270462766947298,0.206507295485425
|
| 281 |
-
bbh,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.5270462766947298,0.206507295485425
|
| 282 |
-
eq_benchv2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,-0.19999999999999998,0.8166666666666667
|
| 283 |
-
eq_benchv2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.19999999999999998,0.8166666666666667
|
| 284 |
-
eq_benchv2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.0,1.0
|
| 285 |
-
eq_benchv2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.0,1.0
|
| 286 |
-
eq_benchv2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,-0.39999999999999997,0.48333333333333334
|
| 287 |
-
eq_benchv2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.39999999999999997,0.48333333333333334
|
| 288 |
-
eq_benchv2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
|
| 289 |
-
eq_benchv2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.7999999999999999,0.08333333333333333
|
| 290 |
-
eq_benchv2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.19999999999999998,0.8166666666666667
|
| 291 |
-
eq_benchv2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.7999999999999999,0.08333333333333333
|
| 292 |
-
gpt4all,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.7378647873726218,0.07697417298126676
|
| 293 |
-
gpt4all,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
|
| 294 |
-
gpt4all,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.31622776601683794,0.44848886103153174
|
| 295 |
-
gpt4all,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.39999999999999997,0.48333333333333334
|
| 296 |
-
gpt4all,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.31622776601683794,0.44848886103153174
|
| 297 |
-
gpt4all,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.39999999999999997,0.48333333333333334
|
| 298 |
-
gpt4all,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,-0.39999999999999997,0.48333333333333334
|
| 299 |
-
gpt4all,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,-0.39999999999999997,0.48333333333333334
|
| 300 |
-
gpt4all,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.39999999999999997,0.48333333333333334
|
| 301 |
-
gpt4all,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.5270462766947298,0.206507295485425
|
| 302 |
-
hugging_6,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,-0.6,0.23333333333333334
|
| 303 |
-
hugging_6,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,-0.6,0.23333333333333334
|
| 304 |
-
hugging_6,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.19999999999999998,0.8166666666666667
|
| 305 |
-
hugging_6,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.39999999999999997,0.48333333333333334
|
| 306 |
-
hugging_6,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.19999999999999998,0.8166666666666667
|
| 307 |
-
hugging_6,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.6,0.23333333333333334
|
| 308 |
-
hugging_6,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,-0.39999999999999997,0.48333333333333334
|
| 309 |
-
hugging_6,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,-0.6,0.23333333333333334
|
| 310 |
-
hugging_6,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,-0.39999999999999997,0.48333333333333334
|
| 311 |
-
hugging_6,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.6,0.23333333333333334
|
| 312 |
-
llmonitor,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.11952286093343936,0.7815112949987133
|
| 313 |
-
llmonitor,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.0,1.0
|
| 314 |
-
llmonitor,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.0,1.0
|
| 315 |
-
llmonitor,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.6,0.23333333333333334
|
| 316 |
-
llmonitor,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.39999999999999997,0.48333333333333334
|
| 317 |
-
llmonitor,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.6,0.23333333333333334
|
| 318 |
-
llmonitor,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.35856858280031806,0.40538055645894233
|
| 319 |
-
llmonitor,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.31622776601683794,0.44848886103153174
|
| 320 |
-
llmonitor,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.0,1.0
|
| 321 |
-
llmonitor,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.5270462766947298,0.206507295485425
|
| 322 |
-
magi,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.39999999999999997,0.48333333333333334
|
| 323 |
-
magi,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.19999999999999998,0.8166666666666667
|
| 324 |
-
magi,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,-0.10540925533894598,0.8005421074231263
|
| 325 |
-
magi,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.39999999999999997,0.48333333333333334
|
| 326 |
-
magi,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.6,0.23333333333333334
|
| 327 |
-
magi,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.7999999999999999,0.08333333333333333
|
| 328 |
-
magi,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.6,0.23333333333333334
|
| 329 |
-
magi,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.7999999999999999,0.08333333333333333
|
| 330 |
-
magi,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.19999999999999998,0.8166666666666667
|
| 331 |
-
magi,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,-0.19999999999999998,0.8166666666666667
|
| 332 |
-
mmlu,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.6,0.23333333333333334
|
| 333 |
-
mmlu,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
|
| 334 |
-
mmlu,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.0,1.0
|
| 335 |
-
mmlu,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.39999999999999997,0.48333333333333334
|
| 336 |
-
mmlu,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.6,0.23333333333333334
|
| 337 |
-
mmlu,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.6,0.23333333333333334
|
| 338 |
-
mmlu,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.6,0.23333333333333334
|
| 339 |
-
mmlu,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
|
| 340 |
-
mmlu,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.6,0.23333333333333334
|
| 341 |
-
mmlu,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.5270462766947298,0.206507295485425
|
| 342 |
-
mt_bench,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.6,0.23333333333333334
|
| 343 |
-
mt_bench,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.0,1.0
|
| 344 |
-
mt_bench,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.10540925533894598,0.8005421074231263
|
| 345 |
-
mt_bench,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.39999999999999997,0.48333333333333334
|
| 346 |
-
mt_bench,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.39999999999999997,0.48333333333333334
|
| 347 |
-
mt_bench,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.19999999999999998,0.8166666666666667
|
| 348 |
-
mt_bench,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.10540925533894598,0.8005421074231263
|
| 349 |
-
mt_bench,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,-0.39999999999999997,0.48333333333333334
|
| 350 |
-
mt_bench,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.19999999999999998,0.8166666666666667
|
| 351 |
-
mt_bench,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.39999999999999997,0.48333333333333334
|
| 352 |
-
biggen_mwr,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.39999999999999997,0.48333333333333334
|
| 353 |
-
biggen_mwr,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
|
| 354 |
-
biggen_mwr,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.19999999999999998,0.8166666666666667
|
| 355 |
-
biggen_mwr,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.6,0.23333333333333334
|
| 356 |
-
biggen_mwr,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.6,0.23333333333333334
|
| 357 |
-
biggen_mwr,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.39999999999999997,0.48333333333333334
|
| 358 |
-
biggen_mwr,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
|
| 359 |
-
biggen_mwr,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.39999999999999997,0.48333333333333334
|
| 360 |
-
biggen_mwr,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.6,0.23333333333333334
|
| 361 |
-
biggen_mwr,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.7999999999999999,0.08333333333333333
|
| 362 |
-
aggregate,holistic,hellaswag,BLZ_240312,kendall,somewhere_aggregate,5,0,0.0,1.0
|
| 363 |
-
aggregate,holistic,hellaswag,BLZ_240312,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
|
| 364 |
-
aggregate,holistic,hellaswag,BLZ_240312,kendall,somewhere_aggregate,5,2,-0.19999999999999998,0.8166666666666667
|
| 365 |
-
aggregate,holistic,hellaswag,BLZ_240312,kendall,somewhere_aggregate,5,3,0.6,0.23333333333333334
|
| 366 |
-
aggregate,holistic,hellaswag,BLZ_240312,kendall,somewhere_aggregate,5,4,0.39999999999999997,0.48333333333333334
|
| 367 |
-
aggregate,holistic,hellaswag,BLZ_240312,kendall,somewhere_aggregate,5,5,0.19999999999999998,0.8166666666666667
|
| 368 |
-
aggregate,holistic,hellaswag,BLZ_240312,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
|
| 369 |
-
aggregate,holistic,hellaswag,BLZ_240312,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
|
| 370 |
-
aggregate,holistic,hellaswag,BLZ_240312,kendall,somewhere_aggregate,5,8,0.39999999999999997,0.48333333333333334
|
| 371 |
-
aggregate,holistic,hellaswag,BLZ_240312,kendall,somewhere_aggregate,5,9,0.6,0.23333333333333334
|
| 372 |
-
aggregate,holistic,humaneval,BLZ_240312,kendall,somewhere_aggregate,5,0,-0.39999999999999997,0.48333333333333334
|
| 373 |
-
aggregate,holistic,humaneval,BLZ_240312,kendall,somewhere_aggregate,5,1,-0.5270462766947298,0.206507295485425
|
| 374 |
-
aggregate,holistic,humaneval,BLZ_240312,kendall,somewhere_aggregate,5,2,0.5270462766947298,0.206507295485425
|
| 375 |
-
aggregate,holistic,humaneval,BLZ_240312,kendall,somewhere_aggregate,5,3,0.5270462766947298,0.206507295485425
|
| 376 |
-
aggregate,holistic,humaneval,BLZ_240312,kendall,somewhere_aggregate,5,4,-0.22360679774997896,0.6015081344405899
|
| 377 |
-
aggregate,holistic,humaneval,BLZ_240312,kendall,somewhere_aggregate,5,5,0.10540925533894598,0.8005421074231263
|
| 378 |
-
aggregate,holistic,humaneval,BLZ_240312,kendall,somewhere_aggregate,5,6,-0.10540925533894598,0.8005421074231263
|
| 379 |
-
aggregate,holistic,humaneval,BLZ_240312,kendall,somewhere_aggregate,5,7,0.39999999999999997,0.48333333333333334
|
| 380 |
-
aggregate,holistic,humaneval,BLZ_240312,kendall,somewhere_aggregate,5,8,-0.10540925533894598,0.8005421074231263
|
| 381 |
-
aggregate,holistic,humaneval,BLZ_240312,kendall,somewhere_aggregate,5,9,-0.22360679774997896,0.6015081344405899
|
| 382 |
-
aggregate,holistic,mbpp,BLZ_240312,kendall,somewhere_aggregate,5,0,0.10540925533894598,0.8005421074231263
|
| 383 |
-
aggregate,holistic,mbpp,BLZ_240312,kendall,somewhere_aggregate,5,1,-0.31622776601683794,0.44848886103153174
|
| 384 |
-
aggregate,holistic,mbpp,BLZ_240312,kendall,somewhere_aggregate,5,2,-0.31622776601683794,0.44848886103153174
|
| 385 |
-
aggregate,holistic,mbpp,BLZ_240312,kendall,somewhere_aggregate,5,3,0.10540925533894598,0.8005421074231263
|
| 386 |
-
aggregate,holistic,mbpp,BLZ_240312,kendall,somewhere_aggregate,5,4,-0.39999999999999997,0.48333333333333334
|
| 387 |
-
aggregate,holistic,mbpp,BLZ_240312,kendall,somewhere_aggregate,5,5,0.10540925533894598,0.8005421074231263
|
| 388 |
-
aggregate,holistic,mbpp,BLZ_240312,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
|
| 389 |
-
aggregate,holistic,mbpp,BLZ_240312,kendall,somewhere_aggregate,5,7,0.39999999999999997,0.48333333333333334
|
| 390 |
-
aggregate,holistic,mbpp,BLZ_240312,kendall,somewhere_aggregate,5,8,0.10540925533894598,0.8005421074231263
|
| 391 |
-
aggregate,holistic,mbpp,BLZ_240312,kendall,somewhere_aggregate,5,9,0.39999999999999997,0.48333333333333334
|
| 392 |
-
aggregate,holistic,winogrande,BLZ_240312,kendall,somewhere_aggregate,5,0,-0.19999999999999998,0.8166666666666667
|
| 393 |
-
aggregate,holistic,winogrande,BLZ_240312,kendall,somewhere_aggregate,5,1,0.7999999999999999,0.08333333333333333
|
| 394 |
-
aggregate,holistic,winogrande,BLZ_240312,kendall,somewhere_aggregate,5,2,0.0,1.0
|
| 395 |
-
aggregate,holistic,winogrande,BLZ_240312,kendall,somewhere_aggregate,5,3,-0.19999999999999998,0.8166666666666667
|
| 396 |
-
aggregate,holistic,winogrande,BLZ_240312,kendall,somewhere_aggregate,5,4,0.31622776601683794,0.44848886103153174
|
| 397 |
-
aggregate,holistic,winogrande,BLZ_240312,kendall,somewhere_aggregate,5,5,0.7999999999999999,0.08333333333333333
|
| 398 |
-
aggregate,holistic,winogrande,BLZ_240312,kendall,somewhere_aggregate,5,6,-0.9999999999999999,0.016666666666666666
|
| 399 |
-
aggregate,holistic,winogrande,BLZ_240312,kendall,somewhere_aggregate,5,7,0.7999999999999999,0.08333333333333333
|
| 400 |
-
aggregate,holistic,winogrande,BLZ_240312,kendall,somewhere_aggregate,5,8,0.0,1.0
|
| 401 |
-
aggregate,holistic,winogrande,BLZ_240312,kendall,somewhere_aggregate,5,9,-0.19999999999999998,0.8166666666666667
|
| 402 |
-
aggregate,holistic,grounding,biggen_240612,kendall,somewhere_aggregate,5,0,0.9486832980505137,0.02297740150320607
|
| 403 |
-
aggregate,holistic,grounding,biggen_240612,kendall,somewhere_aggregate,5,1,0.19999999999999998,0.8166666666666667
|
| 404 |
-
aggregate,holistic,grounding,biggen_240612,kendall,somewhere_aggregate,5,2,0.10540925533894598,0.8005421074231263
|
| 405 |
-
aggregate,holistic,grounding,biggen_240612,kendall,somewhere_aggregate,5,3,0.31622776601683794,0.44848886103153174
|
| 406 |
-
aggregate,holistic,grounding,biggen_240612,kendall,somewhere_aggregate,5,4,0.9486832980505137,0.02297740150320607
|
| 407 |
-
aggregate,holistic,grounding,biggen_240612,kendall,somewhere_aggregate,5,5,0.9486832980505137,0.02297740150320607
|
| 408 |
-
aggregate,holistic,grounding,biggen_240612,kendall,somewhere_aggregate,5,6,0.31622776601683794,0.44848886103153174
|
| 409 |
-
aggregate,holistic,grounding,biggen_240612,kendall,somewhere_aggregate,5,7,0.19999999999999998,0.8166666666666667
|
| 410 |
-
aggregate,holistic,grounding,biggen_240612,kendall,somewhere_aggregate,5,8,0.39999999999999997,0.48333333333333334
|
| 411 |
-
aggregate,holistic,grounding,biggen_240612,kendall,somewhere_aggregate,5,9,0.19999999999999998,0.8166666666666667
|
| 412 |
-
aggregate,holistic,instruction_following,biggen_240612,kendall,somewhere_aggregate,5,0,0.0,1.0
|
| 413 |
-
aggregate,holistic,instruction_following,biggen_240612,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
|
| 414 |
-
aggregate,holistic,instruction_following,biggen_240612,kendall,somewhere_aggregate,5,2,0.7378647873726218,0.07697417298126676
|
| 415 |
-
aggregate,holistic,instruction_following,biggen_240612,kendall,somewhere_aggregate,5,3,-0.39999999999999997,0.48333333333333334
|
| 416 |
-
aggregate,holistic,instruction_following,biggen_240612,kendall,somewhere_aggregate,5,4,0.8944271909999159,0.0367138563627041
|
| 417 |
-
aggregate,holistic,instruction_following,biggen_240612,kendall,somewhere_aggregate,5,5,0.9486832980505137,0.02297740150320607
|
| 418 |
-
aggregate,holistic,instruction_following,biggen_240612,kendall,somewhere_aggregate,5,6,0.9486832980505137,0.02297740150320607
|
| 419 |
-
aggregate,holistic,instruction_following,biggen_240612,kendall,somewhere_aggregate,5,7,0.0,1.0
|
| 420 |
-
aggregate,holistic,instruction_following,biggen_240612,kendall,somewhere_aggregate,5,8,0.8944271909999159,0.0367138563627041
|
| 421 |
-
aggregate,holistic,instruction_following,biggen_240612,kendall,somewhere_aggregate,5,9,0.7378647873726218,0.07697417298126676
|
| 422 |
-
aggregate,holistic,planning,biggen_240612,kendall,somewhere_aggregate,5,0,0.7378647873726218,0.07697417298126676
|
| 423 |
-
aggregate,holistic,planning,biggen_240612,kendall,somewhere_aggregate,5,1,0.7999999999999999,0.08333333333333333
|
| 424 |
-
aggregate,holistic,planning,biggen_240612,kendall,somewhere_aggregate,5,2,0.39999999999999997,0.48333333333333334
|
| 425 |
-
aggregate,holistic,planning,biggen_240612,kendall,somewhere_aggregate,5,3,0.39999999999999997,0.48333333333333334
|
| 426 |
-
aggregate,holistic,planning,biggen_240612,kendall,somewhere_aggregate,5,4,0.19999999999999998,0.8166666666666667
|
| 427 |
-
aggregate,holistic,planning,biggen_240612,kendall,somewhere_aggregate,5,5,0.39999999999999997,0.48333333333333334
|
| 428 |
-
aggregate,holistic,planning,biggen_240612,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
|
| 429 |
-
aggregate,holistic,planning,biggen_240612,kendall,somewhere_aggregate,5,7,0.7378647873726218,0.07697417298126676
|
| 430 |
-
aggregate,holistic,planning,biggen_240612,kendall,somewhere_aggregate,5,8,-0.10540925533894598,0.8005421074231263
|
| 431 |
-
aggregate,holistic,planning,biggen_240612,kendall,somewhere_aggregate,5,9,0.7378647873726218,0.07697417298126676
|
| 432 |
-
aggregate,holistic,reasoning,biggen_240612,kendall,somewhere_aggregate,5,0,0.7378647873726218,0.07697417298126676
|
| 433 |
-
aggregate,holistic,reasoning,biggen_240612,kendall,somewhere_aggregate,5,1,0.6,0.23333333333333334
|
| 434 |
-
aggregate,holistic,reasoning,biggen_240612,kendall,somewhere_aggregate,5,2,0.7378647873726218,0.07697417298126676
|
| 435 |
-
aggregate,holistic,reasoning,biggen_240612,kendall,somewhere_aggregate,5,3,0.6,0.23333333333333334
|
| 436 |
-
aggregate,holistic,reasoning,biggen_240612,kendall,somewhere_aggregate,5,4,0.5270462766947298,0.206507295485425
|
| 437 |
-
aggregate,holistic,reasoning,biggen_240612,kendall,somewhere_aggregate,5,5,0.7999999999999999,0.08333333333333333
|
| 438 |
-
aggregate,holistic,reasoning,biggen_240612,kendall,somewhere_aggregate,5,6,0.5270462766947298,0.206507295485425
|
| 439 |
-
aggregate,holistic,reasoning,biggen_240612,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
|
| 440 |
-
aggregate,holistic,reasoning,biggen_240612,kendall,somewhere_aggregate,5,8,0.0,1.0
|
| 441 |
-
aggregate,holistic,reasoning,biggen_240612,kendall,somewhere_aggregate,5,9,0.39999999999999997,0.48333333333333334
|
| 442 |
-
aggregate,holistic,refinement,biggen_240612,kendall,somewhere_aggregate,5,0,0.6,0.23333333333333334
|
| 443 |
-
aggregate,holistic,refinement,biggen_240612,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
|
| 444 |
-
aggregate,holistic,refinement,biggen_240612,kendall,somewhere_aggregate,5,2,0.19999999999999998,0.8166666666666667
|
| 445 |
-
aggregate,holistic,refinement,biggen_240612,kendall,somewhere_aggregate,5,3,0.39999999999999997,0.48333333333333334
|
| 446 |
-
aggregate,holistic,refinement,biggen_240612,kendall,somewhere_aggregate,5,4,0.39999999999999997,0.48333333333333334
|
| 447 |
-
aggregate,holistic,refinement,biggen_240612,kendall,somewhere_aggregate,5,5,0.39999999999999997,0.48333333333333334
|
| 448 |
-
aggregate,holistic,refinement,biggen_240612,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
|
| 449 |
-
aggregate,holistic,refinement,biggen_240612,kendall,somewhere_aggregate,5,7,0.39999999999999997,0.48333333333333334
|
| 450 |
-
aggregate,holistic,refinement,biggen_240612,kendall,somewhere_aggregate,5,8,0.39999999999999997,0.48333333333333334
|
| 451 |
-
aggregate,holistic,refinement,biggen_240612,kendall,somewhere_aggregate,5,9,0.6,0.23333333333333334
|
| 452 |
-
aggregate,holistic,safety,biggen_240612,kendall,somewhere_aggregate,5,0,0.0,1.0
|
| 453 |
-
aggregate,holistic,safety,biggen_240612,kendall,somewhere_aggregate,5,1,0.0,1.0
|
| 454 |
-
aggregate,holistic,safety,biggen_240612,kendall,somewhere_aggregate,5,2,-0.19999999999999998,0.8166666666666667
|
| 455 |
-
aggregate,holistic,safety,biggen_240612,kendall,somewhere_aggregate,5,3,0.0,1.0
|
| 456 |
-
aggregate,holistic,safety,biggen_240612,kendall,somewhere_aggregate,5,4,-0.19999999999999998,0.8166666666666667
|
| 457 |
-
aggregate,holistic,safety,biggen_240612,kendall,somewhere_aggregate,5,5,-0.6,0.23333333333333334
|
| 458 |
-
aggregate,holistic,safety,biggen_240612,kendall,somewhere_aggregate,5,6,0.7999999999999999,0.08333333333333333
|
| 459 |
-
aggregate,holistic,safety,biggen_240612,kendall,somewhere_aggregate,5,7,-0.6,0.23333333333333334
|
| 460 |
-
aggregate,holistic,safety,biggen_240612,kendall,somewhere_aggregate,5,8,0.6,0.23333333333333334
|
| 461 |
-
aggregate,holistic,safety,biggen_240612,kendall,somewhere_aggregate,5,9,0.6,0.23333333333333334
|
| 462 |
-
aggregate,holistic,theory_of_mind,biggen_240612,kendall,somewhere_aggregate,5,0,0.19999999999999998,0.8166666666666667
|
| 463 |
-
aggregate,holistic,theory_of_mind,biggen_240612,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
|
| 464 |
-
aggregate,holistic,theory_of_mind,biggen_240612,kendall,somewhere_aggregate,5,2,0.6,0.23333333333333334
|
| 465 |
-
aggregate,holistic,theory_of_mind,biggen_240612,kendall,somewhere_aggregate,5,3,0.0,1.0
|
| 466 |
-
aggregate,holistic,theory_of_mind,biggen_240612,kendall,somewhere_aggregate,5,4,0.19999999999999998,0.8166666666666667
|
| 467 |
-
aggregate,holistic,theory_of_mind,biggen_240612,kendall,somewhere_aggregate,5,5,0.19999999999999998,0.8166666666666667
|
| 468 |
-
aggregate,holistic,theory_of_mind,biggen_240612,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
|
| 469 |
-
aggregate,holistic,theory_of_mind,biggen_240612,kendall,somewhere_aggregate,5,7,0.0,1.0
|
| 470 |
-
aggregate,holistic,theory_of_mind,biggen_240612,kendall,somewhere_aggregate,5,8,0.19999999999999998,0.8166666666666667
|
| 471 |
-
aggregate,holistic,theory_of_mind,biggen_240612,kendall,somewhere_aggregate,5,9,0.39999999999999997,0.48333333333333334
|
| 472 |
-
aggregate,holistic,tool_usage,biggen_240612,kendall,somewhere_aggregate,5,0,0.19999999999999998,0.8166666666666667
|
| 473 |
-
aggregate,holistic,tool_usage,biggen_240612,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
|
| 474 |
-
aggregate,holistic,tool_usage,biggen_240612,kendall,somewhere_aggregate,5,2,0.9999999999999999,0.016666666666666666
|
| 475 |
-
aggregate,holistic,tool_usage,biggen_240612,kendall,somewhere_aggregate,5,3,0.9999999999999999,0.016666666666666666
|
| 476 |
-
aggregate,holistic,tool_usage,biggen_240612,kendall,somewhere_aggregate,5,4,0.39999999999999997,0.48333333333333334
|
| 477 |
-
aggregate,holistic,tool_usage,biggen_240612,kendall,somewhere_aggregate,5,5,0.9999999999999999,0.016666666666666666
|
| 478 |
-
aggregate,holistic,tool_usage,biggen_240612,kendall,somewhere_aggregate,5,6,0.19999999999999998,0.8166666666666667
|
| 479 |
-
aggregate,holistic,tool_usage,biggen_240612,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
|
| 480 |
-
aggregate,holistic,tool_usage,biggen_240612,kendall,somewhere_aggregate,5,8,0.7999999999999999,0.08333333333333333
|
| 481 |
-
aggregate,holistic,tool_usage,biggen_240612,kendall,somewhere_aggregate,5,9,0.39999999999999997,0.48333333333333334
|
| 482 |
-
aggregate,holistic,livebench_average,livebench_240701,kendall,somewhere_aggregate,5,0,0.6,0.23333333333333334
|
| 483 |
-
aggregate,holistic,livebench_average,livebench_240701,kendall,somewhere_aggregate,5,1,0.7999999999999999,0.08333333333333333
|
| 484 |
-
aggregate,holistic,livebench_average,livebench_240701,kendall,somewhere_aggregate,5,2,0.7999999999999999,0.08333333333333333
|
| 485 |
-
aggregate,holistic,livebench_average,livebench_240701,kendall,somewhere_aggregate,5,3,0.6,0.23333333333333334
|
| 486 |
-
aggregate,holistic,livebench_average,livebench_240701,kendall,somewhere_aggregate,5,4,0.6,0.23333333333333334
|
| 487 |
-
aggregate,holistic,livebench_average,livebench_240701,kendall,somewhere_aggregate,5,5,0.39999999999999997,0.48333333333333334
|
| 488 |
-
aggregate,holistic,livebench_average,livebench_240701,kendall,somewhere_aggregate,5,6,0.6,0.23333333333333334
|
| 489 |
-
aggregate,holistic,livebench_average,livebench_240701,kendall,somewhere_aggregate,5,7,0.7999999999999999,0.08333333333333333
|
| 490 |
-
aggregate,holistic,livebench_average,livebench_240701,kendall,somewhere_aggregate,5,8,0.39999999999999997,0.48333333333333334
|
| 491 |
-
aggregate,holistic,livebench_average,livebench_240701,kendall,somewhere_aggregate,5,9,0.39999999999999997,0.48333333333333334
|
| 492 |
-
aggregate,holistic,reasoning_average,livebench_240701,kendall,somewhere_aggregate,5,0,0.7378647873726218,0.07697417298126676
|
| 493 |
-
aggregate,holistic,reasoning_average,livebench_240701,kendall,somewhere_aggregate,5,1,0.5270462766947298,0.206507295485425
|
| 494 |
-
aggregate,holistic,reasoning_average,livebench_240701,kendall,somewhere_aggregate,5,2,0.7378647873726218,0.07697417298126676
|
| 495 |
-
aggregate,holistic,reasoning_average,livebench_240701,kendall,somewhere_aggregate,5,3,0.7378647873726218,0.07697417298126676
|
| 496 |
-
aggregate,holistic,reasoning_average,livebench_240701,kendall,somewhere_aggregate,5,4,0.5270462766947298,0.206507295485425
|
| 497 |
-
aggregate,holistic,reasoning_average,livebench_240701,kendall,somewhere_aggregate,5,5,0.7999999999999999,0.08333333333333333
|
| 498 |
-
aggregate,holistic,reasoning_average,livebench_240701,kendall,somewhere_aggregate,5,6,0.7378647873726218,0.07697417298126676
|
| 499 |
-
aggregate,holistic,reasoning_average,livebench_240701,kendall,somewhere_aggregate,5,7,0.7999999999999999,0.08333333333333333
|
| 500 |
-
aggregate,holistic,reasoning_average,livebench_240701,kendall,somewhere_aggregate,5,8,0.5270462766947298,0.206507295485425
|
| 501 |
-
aggregate,holistic,reasoning_average,livebench_240701,kendall,somewhere_aggregate,5,9,0.7378647873726218,0.07697417298126676
|
| 502 |
-
aggregate,holistic,coding_average,livebench_240701,kendall,somewhere_aggregate,5,0,0.31622776601683794,0.44848886103153174
|
| 503 |
-
aggregate,holistic,coding_average,livebench_240701,kendall,somewhere_aggregate,5,1,0.31622776601683794,0.44848886103153174
|
| 504 |
-
aggregate,holistic,coding_average,livebench_240701,kendall,somewhere_aggregate,5,2,0.6,0.23333333333333334
|
| 505 |
-
aggregate,holistic,coding_average,livebench_240701,kendall,somewhere_aggregate,5,3,0.31622776601683794,0.44848886103153174
|
| 506 |
-
aggregate,holistic,coding_average,livebench_240701,kendall,somewhere_aggregate,5,4,0.31622776601683794,0.44848886103153174
|
| 507 |
-
aggregate,holistic,coding_average,livebench_240701,kendall,somewhere_aggregate,5,5,0.5270462766947298,0.206507295485425
|
| 508 |
-
aggregate,holistic,coding_average,livebench_240701,kendall,somewhere_aggregate,5,6,0.5270462766947298,0.206507295485425
|
| 509 |
-
aggregate,holistic,coding_average,livebench_240701,kendall,somewhere_aggregate,5,7,0.5270462766947298,0.206507295485425
|
| 510 |
-
aggregate,holistic,coding_average,livebench_240701,kendall,somewhere_aggregate,5,8,0.5270462766947298,0.206507295485425
|
| 511 |
-
aggregate,holistic,coding_average,livebench_240701,kendall,somewhere_aggregate,5,9,0.5270462766947298,0.206507295485425
|
| 512 |
-
aggregate,holistic,mathematics_average,livebench_240701,kendall,somewhere_aggregate,5,0,0.6,0.23333333333333334
|
| 513 |
-
aggregate,holistic,mathematics_average,livebench_240701,kendall,somewhere_aggregate,5,1,0.6,0.23333333333333334
|
| 514 |
-
aggregate,holistic,mathematics_average,livebench_240701,kendall,somewhere_aggregate,5,2,0.6,0.23333333333333334
|
| 515 |
-
aggregate,holistic,mathematics_average,livebench_240701,kendall,somewhere_aggregate,5,3,0.6,0.23333333333333334
|
| 516 |
-
aggregate,holistic,mathematics_average,livebench_240701,kendall,somewhere_aggregate,5,4,0.6,0.23333333333333334
|
| 517 |
-
aggregate,holistic,mathematics_average,livebench_240701,kendall,somewhere_aggregate,5,5,0.6,0.23333333333333334
|
| 518 |
-
aggregate,holistic,mathematics_average,livebench_240701,kendall,somewhere_aggregate,5,6,0.6,0.23333333333333334
|
| 519 |
-
aggregate,holistic,mathematics_average,livebench_240701,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
|
| 520 |
-
aggregate,holistic,mathematics_average,livebench_240701,kendall,somewhere_aggregate,5,8,0.6,0.23333333333333334
|
| 521 |
-
aggregate,holistic,mathematics_average,livebench_240701,kendall,somewhere_aggregate,5,9,0.6,0.23333333333333334
|
| 522 |
-
aggregate,holistic,data_analysis_average,livebench_240701,kendall,somewhere_aggregate,5,0,0.6,0.23333333333333334
|
| 523 |
-
aggregate,holistic,data_analysis_average,livebench_240701,kendall,somewhere_aggregate,5,1,0.6,0.23333333333333334
|
| 524 |
-
aggregate,holistic,data_analysis_average,livebench_240701,kendall,somewhere_aggregate,5,2,0.6,0.23333333333333334
|
| 525 |
-
aggregate,holistic,data_analysis_average,livebench_240701,kendall,somewhere_aggregate,5,3,0.6,0.23333333333333334
|
| 526 |
-
aggregate,holistic,data_analysis_average,livebench_240701,kendall,somewhere_aggregate,5,4,0.7999999999999999,0.08333333333333333
|
| 527 |
-
aggregate,holistic,data_analysis_average,livebench_240701,kendall,somewhere_aggregate,5,5,0.7999999999999999,0.08333333333333333
|
| 528 |
-
aggregate,holistic,data_analysis_average,livebench_240701,kendall,somewhere_aggregate,5,6,0.7999999999999999,0.08333333333333333
|
| 529 |
-
aggregate,holistic,data_analysis_average,livebench_240701,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
|
| 530 |
-
aggregate,holistic,data_analysis_average,livebench_240701,kendall,somewhere_aggregate,5,8,0.7999999999999999,0.08333333333333333
|
| 531 |
-
aggregate,holistic,data_analysis_average,livebench_240701,kendall,somewhere_aggregate,5,9,0.7999999999999999,0.08333333333333333
|
| 532 |
-
aggregate,holistic,language_average,livebench_240701,kendall,somewhere_aggregate,5,0,0.6,0.23333333333333334
|
| 533 |
-
aggregate,holistic,language_average,livebench_240701,kendall,somewhere_aggregate,5,1,0.7999999999999999,0.08333333333333333
|
| 534 |
-
aggregate,holistic,language_average,livebench_240701,kendall,somewhere_aggregate,5,2,0.7999999999999999,0.08333333333333333
|
| 535 |
-
aggregate,holistic,language_average,livebench_240701,kendall,somewhere_aggregate,5,3,0.7999999999999999,0.08333333333333333
|
| 536 |
-
aggregate,holistic,language_average,livebench_240701,kendall,somewhere_aggregate,5,4,0.7999999999999999,0.08333333333333333
|
| 537 |
-
aggregate,holistic,language_average,livebench_240701,kendall,somewhere_aggregate,5,5,0.7999999999999999,0.08333333333333333
|
| 538 |
-
aggregate,holistic,language_average,livebench_240701,kendall,somewhere_aggregate,5,6,0.6,0.23333333333333334
|
| 539 |
-
aggregate,holistic,language_average,livebench_240701,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
|
| 540 |
-
aggregate,holistic,language_average,livebench_240701,kendall,somewhere_aggregate,5,8,0.6,0.23333333333333334
|
| 541 |
-
aggregate,holistic,language_average,livebench_240701,kendall,somewhere_aggregate,5,9,0.6,0.23333333333333334
|
| 542 |
-
aggregate,holistic,if_average,livebench_240701,kendall,somewhere_aggregate,5,0,0.0,1.0
|
| 543 |
-
aggregate,holistic,if_average,livebench_240701,kendall,somewhere_aggregate,5,1,-0.6,0.23333333333333334
|
| 544 |
-
aggregate,holistic,if_average,livebench_240701,kendall,somewhere_aggregate,5,2,0.19999999999999998,0.8166666666666667
|
| 545 |
-
aggregate,holistic,if_average,livebench_240701,kendall,somewhere_aggregate,5,3,0.19999999999999998,0.8166666666666667
|
| 546 |
-
aggregate,holistic,if_average,livebench_240701,kendall,somewhere_aggregate,5,4,0.19999999999999998,0.8166666666666667
|
| 547 |
-
aggregate,holistic,if_average,livebench_240701,kendall,somewhere_aggregate,5,5,0.19999999999999998,0.8166666666666667
|
| 548 |
-
aggregate,holistic,if_average,livebench_240701,kendall,somewhere_aggregate,5,6,0.19999999999999998,0.8166666666666667
|
| 549 |
-
aggregate,holistic,if_average,livebench_240701,kendall,somewhere_aggregate,5,7,0.19999999999999998,0.8166666666666667
|
| 550 |
-
aggregate,holistic,if_average,livebench_240701,kendall,somewhere_aggregate,5,8,0.0,1.0
|
| 551 |
-
aggregate,holistic,if_average,livebench_240701,kendall,somewhere_aggregate,5,9,0.19999999999999998,0.8166666666666667
|
| 552 |
-
aggregate,holistic,arena_hard,arena_hard_2404,kendall,somewhere_aggregate,5,0,0.39999999999999997,0.48333333333333334
|
| 553 |
-
aggregate,holistic,arena_hard,arena_hard_2404,kendall,somewhere_aggregate,5,1,0.9999999999999999,0.016666666666666666
|
| 554 |
-
aggregate,holistic,arena_hard,arena_hard_2404,kendall,somewhere_aggregate,5,2,0.19999999999999998,0.8166666666666667
|
| 555 |
-
aggregate,holistic,arena_hard,arena_hard_2404,kendall,somewhere_aggregate,5,3,0.7999999999999999,0.08333333333333333
|
| 556 |
-
aggregate,holistic,arena_hard,arena_hard_2404,kendall,somewhere_aggregate,5,4,0.9999999999999999,0.016666666666666666
|
| 557 |
-
aggregate,holistic,arena_hard,arena_hard_2404,kendall,somewhere_aggregate,5,5,0.7999999999999999,0.08333333333333333
|
| 558 |
-
aggregate,holistic,arena_hard,arena_hard_2404,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
|
| 559 |
-
aggregate,holistic,arena_hard,arena_hard_2404,kendall,somewhere_aggregate,5,7,0.9999999999999999,0.016666666666666666
|
| 560 |
-
aggregate,holistic,arena_hard,arena_hard_2404,kendall,somewhere_aggregate,5,8,0.7999999999999999,0.08333333333333333
|
| 561 |
-
aggregate,holistic,arena_hard,arena_hard_2404,kendall,somewhere_aggregate,5,9,0.7999999999999999,0.08333333333333333
|
| 562 |
-
aggregate,holistic,mixeval,mixeval_240601,kendall,somewhere_aggregate,5,0,0.7999999999999999,0.08333333333333333
|
| 563 |
-
aggregate,holistic,mixeval,mixeval_240601,kendall,somewhere_aggregate,5,1,0.7999999999999999,0.08333333333333333
|
| 564 |
-
aggregate,holistic,mixeval,mixeval_240601,kendall,somewhere_aggregate,5,2,0.7999999999999999,0.08333333333333333
|
| 565 |
-
aggregate,holistic,mixeval,mixeval_240601,kendall,somewhere_aggregate,5,3,0.7999999999999999,0.08333333333333333
|
| 566 |
-
aggregate,holistic,mixeval,mixeval_240601,kendall,somewhere_aggregate,5,4,0.7999999999999999,0.08333333333333333
|
| 567 |
-
aggregate,holistic,mixeval,mixeval_240601,kendall,somewhere_aggregate,5,5,0.7999999999999999,0.08333333333333333
|
| 568 |
-
aggregate,holistic,mixeval,mixeval_240601,kendall,somewhere_aggregate,5,6,0.7999999999999999,0.08333333333333333
|
| 569 |
-
aggregate,holistic,mixeval,mixeval_240601,kendall,somewhere_aggregate,5,7,0.7999999999999999,0.08333333333333333
|
| 570 |
-
aggregate,holistic,mixeval,mixeval_240601,kendall,somewhere_aggregate,5,8,0.7999999999999999,0.08333333333333333
|
| 571 |
-
aggregate,holistic,mixeval,mixeval_240601,kendall,somewhere_aggregate,5,9,0.7999999999999999,0.08333333333333333
|
| 572 |
-
aggregate,holistic,agieval,BLZ_240312,kendall,somewhere_aggregate,5,0,0.31622776601683794,0.44848886103153174
|
| 573 |
-
aggregate,holistic,agieval,BLZ_240312,kendall,somewhere_aggregate,5,1,0.31622776601683794,0.44848886103153174
|
| 574 |
-
aggregate,holistic,agieval,BLZ_240312,kendall,somewhere_aggregate,5,2,0.39999999999999997,0.48333333333333334
|
| 575 |
-
aggregate,holistic,agieval,BLZ_240312,kendall,somewhere_aggregate,5,3,0.7999999999999999,0.08333333333333333
|
| 576 |
-
aggregate,holistic,agieval,BLZ_240312,kendall,somewhere_aggregate,5,4,0.7999999999999999,0.08333333333333333
|
| 577 |
-
aggregate,holistic,agieval,BLZ_240312,kendall,somewhere_aggregate,5,5,0.9999999999999999,0.016666666666666666
|
| 578 |
-
aggregate,holistic,agieval,BLZ_240312,kendall,somewhere_aggregate,5,6,0.19999999999999998,0.8166666666666667
|
| 579 |
-
aggregate,holistic,agieval,BLZ_240312,kendall,somewhere_aggregate,5,7,0.19999999999999998,0.8166666666666667
|
| 580 |
-
aggregate,holistic,agieval,BLZ_240312,kendall,somewhere_aggregate,5,8,0.39999999999999997,0.48333333333333334
|
| 581 |
-
aggregate,holistic,agieval,BLZ_240312,kendall,somewhere_aggregate,5,9,0.7999999999999999,0.08333333333333333
|
| 582 |
-
aggregate,holistic,arc_c,BLZ_240312,kendall,somewhere_aggregate,5,0,0.6,0.23333333333333334
|
| 583 |
-
aggregate,holistic,arc_c,BLZ_240312,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
|
| 584 |
-
aggregate,holistic,arc_c,BLZ_240312,kendall,somewhere_aggregate,5,2,-0.19999999999999998,0.8166666666666667
|
| 585 |
-
aggregate,holistic,arc_c,BLZ_240312,kendall,somewhere_aggregate,5,3,-0.39999999999999997,0.48333333333333334
|
| 586 |
-
aggregate,holistic,arc_c,BLZ_240312,kendall,somewhere_aggregate,5,4,0.0,1.0
|
| 587 |
-
aggregate,holistic,arc_c,BLZ_240312,kendall,somewhere_aggregate,5,5,0.6,0.23333333333333334
|
| 588 |
-
aggregate,holistic,arc_c,BLZ_240312,kendall,somewhere_aggregate,5,6,0.31622776601683794,0.44848886103153174
|
| 589 |
-
aggregate,holistic,arc_c,BLZ_240312,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
|
| 590 |
-
aggregate,holistic,arc_c,BLZ_240312,kendall,somewhere_aggregate,5,8,0.39999999999999997,0.48333333333333334
|
| 591 |
-
aggregate,holistic,arc_c,BLZ_240312,kendall,somewhere_aggregate,5,9,0.7378647873726218,0.07697417298126676
|
| 592 |
-
aggregate,holistic,alpacav1,BLZ_240312,kendall,somewhere_aggregate,5,0,-0.31622776601683794,0.44848886103153174
|
| 593 |
-
aggregate,holistic,alpacav1,BLZ_240312,kendall,somewhere_aggregate,5,1,-0.7999999999999999,0.08333333333333333
|
| 594 |
-
aggregate,holistic,alpacav1,BLZ_240312,kendall,somewhere_aggregate,5,2,0.7999999999999999,0.08333333333333333
|
| 595 |
-
aggregate,holistic,alpacav1,BLZ_240312,kendall,somewhere_aggregate,5,3,0.7999999999999999,0.08333333333333333
|
| 596 |
-
aggregate,holistic,alpacav1,BLZ_240312,kendall,somewhere_aggregate,5,4,0.39999999999999997,0.48333333333333334
|
| 597 |
-
aggregate,holistic,alpacav1,BLZ_240312,kendall,somewhere_aggregate,5,5,0.39999999999999997,0.48333333333333334
|
| 598 |
-
aggregate,holistic,alpacav1,BLZ_240312,kendall,somewhere_aggregate,5,6,0.6,0.23333333333333334
|
| 599 |
-
aggregate,holistic,alpacav1,BLZ_240312,kendall,somewhere_aggregate,5,7,0.7378647873726218,0.07697417298126676
|
| 600 |
-
aggregate,holistic,alpacav1,BLZ_240312,kendall,somewhere_aggregate,5,8,0.6,0.23333333333333334
|
| 601 |
-
aggregate,holistic,alpacav1,BLZ_240312,kendall,somewhere_aggregate,5,9,0.31622776601683794,0.44848886103153174
|
| 602 |
-
aggregate,holistic,alpacav2,BLZ_240312,kendall,somewhere_aggregate,5,0,0.39999999999999997,0.48333333333333334
|
| 603 |
-
aggregate,holistic,alpacav2,BLZ_240312,kendall,somewhere_aggregate,5,1,0.19999999999999998,0.8166666666666667
|
| 604 |
-
aggregate,holistic,alpacav2,BLZ_240312,kendall,somewhere_aggregate,5,2,0.39999999999999997,0.48333333333333334
|
| 605 |
-
aggregate,holistic,alpacav2,BLZ_240312,kendall,somewhere_aggregate,5,3,0.7378647873726218,0.07697417298126676
|
| 606 |
-
aggregate,holistic,alpacav2,BLZ_240312,kendall,somewhere_aggregate,5,4,0.39999999999999997,0.48333333333333334
|
| 607 |
-
aggregate,holistic,alpacav2,BLZ_240312,kendall,somewhere_aggregate,5,5,-0.6,0.23333333333333334
|
| 608 |
-
aggregate,holistic,alpacav2,BLZ_240312,kendall,somewhere_aggregate,5,6,-0.39999999999999997,0.48333333333333334
|
| 609 |
-
aggregate,holistic,alpacav2,BLZ_240312,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
|
| 610 |
-
aggregate,holistic,alpacav2,BLZ_240312,kendall,somewhere_aggregate,5,8,0.0,1.0
|
| 611 |
-
aggregate,holistic,alpacav2,BLZ_240312,kendall,somewhere_aggregate,5,9,0.6,0.23333333333333334
|
| 612 |
-
aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,somewhere_aggregate,5,0,0.0,1.0
|
| 613 |
-
aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,somewhere_aggregate,5,1,-0.6,0.23333333333333334
|
| 614 |
-
aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,somewhere_aggregate,5,2,0.7999999999999999,0.08333333333333333
|
| 615 |
-
aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,somewhere_aggregate,5,3,0.0,1.0
|
| 616 |
-
aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,somewhere_aggregate,5,4,0.6,0.23333333333333334
|
| 617 |
-
aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,somewhere_aggregate,5,5,0.39999999999999997,0.48333333333333334
|
| 618 |
-
aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
|
| 619 |
-
aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
|
| 620 |
-
aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,somewhere_aggregate,5,8,-0.39999999999999997,0.48333333333333334
|
| 621 |
-
aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,somewhere_aggregate,5,9,0.0,1.0
|
| 622 |
-
aggregate,holistic,arena_elo,BLZ_240312,kendall,somewhere_aggregate,5,0,0.31622776601683794,0.44848886103153174
|
| 623 |
-
aggregate,holistic,arena_elo,BLZ_240312,kendall,somewhere_aggregate,5,1,0.6,0.23333333333333334
|
| 624 |
-
aggregate,holistic,arena_elo,BLZ_240312,kendall,somewhere_aggregate,5,2,0.31622776601683794,0.44848886103153174
|
| 625 |
-
aggregate,holistic,arena_elo,BLZ_240312,kendall,somewhere_aggregate,5,3,-0.9999999999999999,0.016666666666666666
|
| 626 |
-
aggregate,holistic,arena_elo,BLZ_240312,kendall,somewhere_aggregate,5,4,0.39999999999999997,0.48333333333333334
|
| 627 |
-
aggregate,holistic,arena_elo,BLZ_240312,kendall,somewhere_aggregate,5,5,0.31622776601683794,0.44848886103153174
|
| 628 |
-
aggregate,holistic,arena_elo,BLZ_240312,kendall,somewhere_aggregate,5,6,-0.9999999999999999,0.016666666666666666
|
| 629 |
-
aggregate,holistic,arena_elo,BLZ_240312,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
|
| 630 |
-
aggregate,holistic,arena_elo,BLZ_240312,kendall,somewhere_aggregate,5,8,-0.10540925533894598,0.8005421074231263
|
| 631 |
-
aggregate,holistic,arena_elo,BLZ_240312,kendall,somewhere_aggregate,5,9,0.6,0.23333333333333334
|
| 632 |
-
aggregate,holistic,bbh,BLZ_240312,kendall,somewhere_aggregate,5,0,0.9486832980505137,0.02297740150320607
|
| 633 |
-
aggregate,holistic,bbh,BLZ_240312,kendall,somewhere_aggregate,5,1,0.31622776601683794,0.44848886103153174
|
| 634 |
-
aggregate,holistic,bbh,BLZ_240312,kendall,somewhere_aggregate,5,2,-0.39999999999999997,0.48333333333333334
|
| 635 |
-
aggregate,holistic,bbh,BLZ_240312,kendall,somewhere_aggregate,5,3,0.9999999999999999,0.016666666666666666
|
| 636 |
-
aggregate,holistic,bbh,BLZ_240312,kendall,somewhere_aggregate,5,4,0.0,1.0
|
| 637 |
-
aggregate,holistic,bbh,BLZ_240312,kendall,somewhere_aggregate,5,5,-0.39999999999999997,0.48333333333333334
|
| 638 |
-
aggregate,holistic,bbh,BLZ_240312,kendall,somewhere_aggregate,5,6,0.7999999999999999,0.08333333333333333
|
| 639 |
-
aggregate,holistic,bbh,BLZ_240312,kendall,somewhere_aggregate,5,7,0.7999999999999999,0.08333333333333333
|
| 640 |
-
aggregate,holistic,bbh,BLZ_240312,kendall,somewhere_aggregate,5,8,0.5270462766947298,0.206507295485425
|
| 641 |
-
aggregate,holistic,bbh,BLZ_240312,kendall,somewhere_aggregate,5,9,0.5270462766947298,0.206507295485425
|
| 642 |
-
aggregate,holistic,eq_benchv2,BLZ_240312,kendall,somewhere_aggregate,5,0,-0.19999999999999998,0.8166666666666667
|
| 643 |
-
aggregate,holistic,eq_benchv2,BLZ_240312,kendall,somewhere_aggregate,5,1,0.19999999999999998,0.8166666666666667
|
| 644 |
-
aggregate,holistic,eq_benchv2,BLZ_240312,kendall,somewhere_aggregate,5,2,0.0,1.0
|
| 645 |
-
aggregate,holistic,eq_benchv2,BLZ_240312,kendall,somewhere_aggregate,5,3,0.0,1.0
|
| 646 |
-
aggregate,holistic,eq_benchv2,BLZ_240312,kendall,somewhere_aggregate,5,4,-0.39999999999999997,0.48333333333333334
|
| 647 |
-
aggregate,holistic,eq_benchv2,BLZ_240312,kendall,somewhere_aggregate,5,5,0.39999999999999997,0.48333333333333334
|
| 648 |
-
aggregate,holistic,eq_benchv2,BLZ_240312,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
|
| 649 |
-
aggregate,holistic,eq_benchv2,BLZ_240312,kendall,somewhere_aggregate,5,7,0.7999999999999999,0.08333333333333333
|
| 650 |
-
aggregate,holistic,eq_benchv2,BLZ_240312,kendall,somewhere_aggregate,5,8,0.19999999999999998,0.8166666666666667
|
| 651 |
-
aggregate,holistic,eq_benchv2,BLZ_240312,kendall,somewhere_aggregate,5,9,0.7999999999999999,0.08333333333333333
|
| 652 |
-
aggregate,holistic,gpt4all,BLZ_240312,kendall,somewhere_aggregate,5,0,0.7378647873726218,0.07697417298126676
|
| 653 |
-
aggregate,holistic,gpt4all,BLZ_240312,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
|
| 654 |
-
aggregate,holistic,gpt4all,BLZ_240312,kendall,somewhere_aggregate,5,2,0.31622776601683794,0.44848886103153174
|
| 655 |
-
aggregate,holistic,gpt4all,BLZ_240312,kendall,somewhere_aggregate,5,3,0.39999999999999997,0.48333333333333334
|
| 656 |
-
aggregate,holistic,gpt4all,BLZ_240312,kendall,somewhere_aggregate,5,4,0.31622776601683794,0.44848886103153174
|
| 657 |
-
aggregate,holistic,gpt4all,BLZ_240312,kendall,somewhere_aggregate,5,5,0.39999999999999997,0.48333333333333334
|
| 658 |
-
aggregate,holistic,gpt4all,BLZ_240312,kendall,somewhere_aggregate,5,6,-0.39999999999999997,0.48333333333333334
|
| 659 |
-
aggregate,holistic,gpt4all,BLZ_240312,kendall,somewhere_aggregate,5,7,-0.39999999999999997,0.48333333333333334
|
| 660 |
-
aggregate,holistic,gpt4all,BLZ_240312,kendall,somewhere_aggregate,5,8,0.39999999999999997,0.48333333333333334
|
| 661 |
-
aggregate,holistic,gpt4all,BLZ_240312,kendall,somewhere_aggregate,5,9,0.5270462766947298,0.206507295485425
|
| 662 |
-
aggregate,holistic,hugging_6,BLZ_240312,kendall,somewhere_aggregate,5,0,-0.6,0.23333333333333334
|
| 663 |
-
aggregate,holistic,hugging_6,BLZ_240312,kendall,somewhere_aggregate,5,1,-0.6,0.23333333333333334
|
| 664 |
-
aggregate,holistic,hugging_6,BLZ_240312,kendall,somewhere_aggregate,5,2,0.19999999999999998,0.8166666666666667
|
| 665 |
-
aggregate,holistic,hugging_6,BLZ_240312,kendall,somewhere_aggregate,5,3,0.39999999999999997,0.48333333333333334
|
| 666 |
-
aggregate,holistic,hugging_6,BLZ_240312,kendall,somewhere_aggregate,5,4,0.19999999999999998,0.8166666666666667
|
| 667 |
-
aggregate,holistic,hugging_6,BLZ_240312,kendall,somewhere_aggregate,5,5,0.6,0.23333333333333334
|
| 668 |
-
aggregate,holistic,hugging_6,BLZ_240312,kendall,somewhere_aggregate,5,6,-0.39999999999999997,0.48333333333333334
|
| 669 |
-
aggregate,holistic,hugging_6,BLZ_240312,kendall,somewhere_aggregate,5,7,-0.6,0.23333333333333334
|
| 670 |
-
aggregate,holistic,hugging_6,BLZ_240312,kendall,somewhere_aggregate,5,8,-0.39999999999999997,0.48333333333333334
|
| 671 |
-
aggregate,holistic,hugging_6,BLZ_240312,kendall,somewhere_aggregate,5,9,0.6,0.23333333333333334
|
| 672 |
-
aggregate,holistic,llmonitor,BLZ_240312,kendall,somewhere_aggregate,5,0,0.11952286093343936,0.7815112949987133
|
| 673 |
-
aggregate,holistic,llmonitor,BLZ_240312,kendall,somewhere_aggregate,5,1,0.0,1.0
|
| 674 |
-
aggregate,holistic,llmonitor,BLZ_240312,kendall,somewhere_aggregate,5,2,0.0,1.0
|
| 675 |
-
aggregate,holistic,llmonitor,BLZ_240312,kendall,somewhere_aggregate,5,3,0.6,0.23333333333333334
|
| 676 |
-
aggregate,holistic,llmonitor,BLZ_240312,kendall,somewhere_aggregate,5,4,0.39999999999999997,0.48333333333333334
|
| 677 |
-
aggregate,holistic,llmonitor,BLZ_240312,kendall,somewhere_aggregate,5,5,0.6,0.23333333333333334
|
| 678 |
-
aggregate,holistic,llmonitor,BLZ_240312,kendall,somewhere_aggregate,5,6,0.35856858280031806,0.40538055645894233
|
| 679 |
-
aggregate,holistic,llmonitor,BLZ_240312,kendall,somewhere_aggregate,5,7,0.31622776601683794,0.44848886103153174
|
| 680 |
-
aggregate,holistic,llmonitor,BLZ_240312,kendall,somewhere_aggregate,5,8,0.0,1.0
|
| 681 |
-
aggregate,holistic,llmonitor,BLZ_240312,kendall,somewhere_aggregate,5,9,0.5270462766947298,0.206507295485425
|
| 682 |
-
aggregate,holistic,magi,BLZ_240312,kendall,somewhere_aggregate,5,0,0.39999999999999997,0.48333333333333334
|
| 683 |
-
aggregate,holistic,magi,BLZ_240312,kendall,somewhere_aggregate,5,1,0.19999999999999998,0.8166666666666667
|
| 684 |
-
aggregate,holistic,magi,BLZ_240312,kendall,somewhere_aggregate,5,2,-0.10540925533894598,0.8005421074231263
|
| 685 |
-
aggregate,holistic,magi,BLZ_240312,kendall,somewhere_aggregate,5,3,0.39999999999999997,0.48333333333333334
|
| 686 |
-
aggregate,holistic,magi,BLZ_240312,kendall,somewhere_aggregate,5,4,0.6,0.23333333333333334
|
| 687 |
-
aggregate,holistic,magi,BLZ_240312,kendall,somewhere_aggregate,5,5,0.7999999999999999,0.08333333333333333
|
| 688 |
-
aggregate,holistic,magi,BLZ_240312,kendall,somewhere_aggregate,5,6,0.6,0.23333333333333334
|
| 689 |
-
aggregate,holistic,magi,BLZ_240312,kendall,somewhere_aggregate,5,7,0.7999999999999999,0.08333333333333333
|
| 690 |
-
aggregate,holistic,magi,BLZ_240312,kendall,somewhere_aggregate,5,8,0.19999999999999998,0.8166666666666667
|
| 691 |
-
aggregate,holistic,magi,BLZ_240312,kendall,somewhere_aggregate,5,9,-0.19999999999999998,0.8166666666666667
|
| 692 |
-
aggregate,holistic,mmlu,BLZ_240312,kendall,somewhere_aggregate,5,0,0.6,0.23333333333333334
|
| 693 |
-
aggregate,holistic,mmlu,BLZ_240312,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
|
| 694 |
-
aggregate,holistic,mmlu,BLZ_240312,kendall,somewhere_aggregate,5,2,0.0,1.0
|
| 695 |
-
aggregate,holistic,mmlu,BLZ_240312,kendall,somewhere_aggregate,5,3,0.39999999999999997,0.48333333333333334
|
| 696 |
-
aggregate,holistic,mmlu,BLZ_240312,kendall,somewhere_aggregate,5,4,0.6,0.23333333333333334
|
| 697 |
-
aggregate,holistic,mmlu,BLZ_240312,kendall,somewhere_aggregate,5,5,0.6,0.23333333333333334
|
| 698 |
-
aggregate,holistic,mmlu,BLZ_240312,kendall,somewhere_aggregate,5,6,0.6,0.23333333333333334
|
| 699 |
-
aggregate,holistic,mmlu,BLZ_240312,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
|
| 700 |
-
aggregate,holistic,mmlu,BLZ_240312,kendall,somewhere_aggregate,5,8,0.6,0.23333333333333334
|
| 701 |
-
aggregate,holistic,mmlu,BLZ_240312,kendall,somewhere_aggregate,5,9,0.5270462766947298,0.206507295485425
|
| 702 |
-
aggregate,holistic,mt_bench,BLZ_240312,kendall,somewhere_aggregate,5,0,0.6,0.23333333333333334
|
| 703 |
-
aggregate,holistic,mt_bench,BLZ_240312,kendall,somewhere_aggregate,5,1,0.0,1.0
|
| 704 |
-
aggregate,holistic,mt_bench,BLZ_240312,kendall,somewhere_aggregate,5,2,0.10540925533894598,0.8005421074231263
|
| 705 |
-
aggregate,holistic,mt_bench,BLZ_240312,kendall,somewhere_aggregate,5,3,0.39999999999999997,0.48333333333333334
|
| 706 |
-
aggregate,holistic,mt_bench,BLZ_240312,kendall,somewhere_aggregate,5,4,0.39999999999999997,0.48333333333333334
|
| 707 |
-
aggregate,holistic,mt_bench,BLZ_240312,kendall,somewhere_aggregate,5,5,0.19999999999999998,0.8166666666666667
|
| 708 |
-
aggregate,holistic,mt_bench,BLZ_240312,kendall,somewhere_aggregate,5,6,0.10540925533894598,0.8005421074231263
|
| 709 |
-
aggregate,holistic,mt_bench,BLZ_240312,kendall,somewhere_aggregate,5,7,-0.39999999999999997,0.48333333333333334
|
| 710 |
-
aggregate,holistic,mt_bench,BLZ_240312,kendall,somewhere_aggregate,5,8,0.19999999999999998,0.8166666666666667
|
| 711 |
-
aggregate,holistic,mt_bench,BLZ_240312,kendall,somewhere_aggregate,5,9,0.39999999999999997,0.48333333333333334
|
| 712 |
-
aggregate,holistic,biggen_mwr,biggen_240612,kendall,somewhere_aggregate,5,0,0.39999999999999997,0.48333333333333334
|
| 713 |
-
aggregate,holistic,biggen_mwr,biggen_240612,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
|
| 714 |
-
aggregate,holistic,biggen_mwr,biggen_240612,kendall,somewhere_aggregate,5,2,0.19999999999999998,0.8166666666666667
|
| 715 |
-
aggregate,holistic,biggen_mwr,biggen_240612,kendall,somewhere_aggregate,5,3,0.6,0.23333333333333334
|
| 716 |
-
aggregate,holistic,biggen_mwr,biggen_240612,kendall,somewhere_aggregate,5,4,0.6,0.23333333333333334
|
| 717 |
-
aggregate,holistic,biggen_mwr,biggen_240612,kendall,somewhere_aggregate,5,5,0.39999999999999997,0.48333333333333334
|
| 718 |
-
aggregate,holistic,biggen_mwr,biggen_240612,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
|
| 719 |
-
aggregate,holistic,biggen_mwr,biggen_240612,kendall,somewhere_aggregate,5,7,0.39999999999999997,0.48333333333333334
|
| 720 |
-
aggregate,holistic,biggen_mwr,biggen_240612,kendall,somewhere_aggregate,5,8,0.6,0.23333333333333334
|
| 721 |
-
aggregate,holistic,biggen_mwr,biggen_240612,kendall,somewhere_aggregate,5,9,0.7999999999999999,0.08333333333333333
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
cache/agreements_cache_facdc1028ee0edd9aed491afc51b884d.csv
DELETED
|
@@ -1,73 +0,0 @@
|
|
| 1 |
-
scenario,scenario_source,ref_scenario,ref_source,corr_type,model_select_strategy,model_subset_size_requested,exp_n,correlation,p_value
|
| 2 |
-
hellaswag,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.9999999999999999,0.016666666666666666
|
| 3 |
-
humaneval,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.31622776601683794,0.44848886103153174
|
| 4 |
-
mbpp,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.31622776601683794,0.44848886103153174
|
| 5 |
-
winogrande,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
|
| 6 |
-
grounding,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.7378647873726218,0.07697417298126676
|
| 7 |
-
instruction_following,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.7378647873726218,0.07697417298126676
|
| 8 |
-
planning,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
|
| 9 |
-
reasoning,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.9999999999999999,0.016666666666666666
|
| 10 |
-
refinement,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
|
| 11 |
-
safety,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
|
| 12 |
-
theory_of_mind,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
|
| 13 |
-
tool_usage,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
|
| 14 |
-
livebench_average,livebench_240701,aggregate,holistic,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
|
| 15 |
-
reasoning_average,livebench_240701,aggregate,holistic,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
|
| 16 |
-
coding_average,livebench_240701,aggregate,holistic,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
|
| 17 |
-
mathematics_average,livebench_240701,aggregate,holistic,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
|
| 18 |
-
data_analysis_average,livebench_240701,aggregate,holistic,kendall,top_aggregate,5,0,0.6,0.23333333333333334
|
| 19 |
-
language_average,livebench_240701,aggregate,holistic,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
|
| 20 |
-
if_average,livebench_240701,aggregate,holistic,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
|
| 21 |
-
arena_hard,arena_hard_2404,aggregate,holistic,kendall,top_aggregate,5,0,0.9999999999999999,0.016666666666666666
|
| 22 |
-
mixeval,mixeval_240601,aggregate,holistic,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
|
| 23 |
-
agieval,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.5270462766947298,0.206507295485425
|
| 24 |
-
arc_c,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.6,0.23333333333333334
|
| 25 |
-
alpacav1,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.5270462766947298,0.206507295485425
|
| 26 |
-
alpacav2,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.6,0.23333333333333334
|
| 27 |
-
alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.31622776601683794,0.44848886103153174
|
| 28 |
-
arena_elo,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.9999999999999999,0.016666666666666666
|
| 29 |
-
bbh,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.5270462766947298,0.206507295485425
|
| 30 |
-
eq_benchv2,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.9999999999999999,0.016666666666666666
|
| 31 |
-
gpt4all,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.0,1.0
|
| 32 |
-
hugging_6,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
|
| 33 |
-
llmonitor,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.6,0.23333333333333334
|
| 34 |
-
magi,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.31622776601683794,0.44848886103153174
|
| 35 |
-
mmlu,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
|
| 36 |
-
mt_bench,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.6,0.23333333333333334
|
| 37 |
-
biggen_mwr,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
|
| 38 |
-
aggregate,holistic,hellaswag,BLZ_240312,kendall,top_aggregate,5,0,0.9999999999999999,0.016666666666666666
|
| 39 |
-
aggregate,holistic,humaneval,BLZ_240312,kendall,top_aggregate,5,0,0.31622776601683794,0.44848886103153174
|
| 40 |
-
aggregate,holistic,mbpp,BLZ_240312,kendall,top_aggregate,5,0,0.31622776601683794,0.44848886103153174
|
| 41 |
-
aggregate,holistic,winogrande,BLZ_240312,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
|
| 42 |
-
aggregate,holistic,grounding,biggen_240612,kendall,top_aggregate,5,0,0.7378647873726218,0.07697417298126676
|
| 43 |
-
aggregate,holistic,instruction_following,biggen_240612,kendall,top_aggregate,5,0,0.7378647873726218,0.07697417298126676
|
| 44 |
-
aggregate,holistic,planning,biggen_240612,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
|
| 45 |
-
aggregate,holistic,reasoning,biggen_240612,kendall,top_aggregate,5,0,0.9999999999999999,0.016666666666666666
|
| 46 |
-
aggregate,holistic,refinement,biggen_240612,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
|
| 47 |
-
aggregate,holistic,safety,biggen_240612,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
|
| 48 |
-
aggregate,holistic,theory_of_mind,biggen_240612,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
|
| 49 |
-
aggregate,holistic,tool_usage,biggen_240612,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
|
| 50 |
-
aggregate,holistic,livebench_average,livebench_240701,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
|
| 51 |
-
aggregate,holistic,reasoning_average,livebench_240701,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
|
| 52 |
-
aggregate,holistic,coding_average,livebench_240701,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
|
| 53 |
-
aggregate,holistic,mathematics_average,livebench_240701,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
|
| 54 |
-
aggregate,holistic,data_analysis_average,livebench_240701,kendall,top_aggregate,5,0,0.6,0.23333333333333334
|
| 55 |
-
aggregate,holistic,language_average,livebench_240701,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
|
| 56 |
-
aggregate,holistic,if_average,livebench_240701,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
|
| 57 |
-
aggregate,holistic,arena_hard,arena_hard_2404,kendall,top_aggregate,5,0,0.9999999999999999,0.016666666666666666
|
| 58 |
-
aggregate,holistic,mixeval,mixeval_240601,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
|
| 59 |
-
aggregate,holistic,agieval,BLZ_240312,kendall,top_aggregate,5,0,0.5270462766947298,0.206507295485425
|
| 60 |
-
aggregate,holistic,arc_c,BLZ_240312,kendall,top_aggregate,5,0,0.6,0.23333333333333334
|
| 61 |
-
aggregate,holistic,alpacav1,BLZ_240312,kendall,top_aggregate,5,0,0.5270462766947298,0.206507295485425
|
| 62 |
-
aggregate,holistic,alpacav2,BLZ_240312,kendall,top_aggregate,5,0,0.6,0.23333333333333334
|
| 63 |
-
aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,top_aggregate,5,0,0.31622776601683794,0.44848886103153174
|
| 64 |
-
aggregate,holistic,arena_elo,BLZ_240312,kendall,top_aggregate,5,0,0.9999999999999999,0.016666666666666666
|
| 65 |
-
aggregate,holistic,bbh,BLZ_240312,kendall,top_aggregate,5,0,0.5270462766947298,0.206507295485425
|
| 66 |
-
aggregate,holistic,eq_benchv2,BLZ_240312,kendall,top_aggregate,5,0,0.9999999999999999,0.016666666666666666
|
| 67 |
-
aggregate,holistic,gpt4all,BLZ_240312,kendall,top_aggregate,5,0,0.0,1.0
|
| 68 |
-
aggregate,holistic,hugging_6,BLZ_240312,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
|
| 69 |
-
aggregate,holistic,llmonitor,BLZ_240312,kendall,top_aggregate,5,0,0.6,0.23333333333333334
|
| 70 |
-
aggregate,holistic,magi,BLZ_240312,kendall,top_aggregate,5,0,0.31622776601683794,0.44848886103153174
|
| 71 |
-
aggregate,holistic,mmlu,BLZ_240312,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
|
| 72 |
-
aggregate,holistic,mt_bench,BLZ_240312,kendall,top_aggregate,5,0,0.6,0.23333333333333334
|
| 73 |
-
aggregate,holistic,biggen_mwr,biggen_240612,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|