Spaces:
Runtime error
Runtime error
Yotam-Perlitz
commited on
Commit
·
b9a3a5d
1
Parent(s):
ae274a0
add cache
Browse filesSigned-off-by: Yotam-Perlitz <y.perlitz@ibm.com>
cache/aggregate_scoress_cache_741f08262e15cba4bd6c8b25f2b138ca.csv
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
model,score
|
| 2 |
+
claude_3_5_sonnet_20240620,1.0
|
| 3 |
+
gpt_4o_2024_05_13,0.9833333333333333
|
| 4 |
+
gpt_4_0125_preview,0.9666666666666667
|
| 5 |
+
gpt_4o_2024_08_06,0.95
|
| 6 |
+
athene_70b,0.9333333333333333
|
| 7 |
+
gpt_4o_mini,0.9166666666666666
|
| 8 |
+
gemini_1_5_pro_api_preview,0.9
|
| 9 |
+
mistral_large_2407,0.8833333333333333
|
| 10 |
+
llama3_1_405b_instruct,0.8666666666666667
|
| 11 |
+
glm_4_0520,0.85
|
| 12 |
+
yi_large,0.8333333333333334
|
| 13 |
+
deepseek_coder_v2,0.8166666666666667
|
| 14 |
+
claude_3_opus_20240229,0.8
|
| 15 |
+
gemma_2_27b_it,0.7833333333333333
|
| 16 |
+
llama3_1_70b_instruct,0.75
|
| 17 |
+
glm_4_0116,0.75
|
| 18 |
+
glm_4_air,0.7333333333333333
|
| 19 |
+
gpt_4_0314,0.7166666666666667
|
| 20 |
+
gemini_1_5_flash_api_preview,0.7
|
| 21 |
+
qwen2_72b_instruct,0.6833333333333333
|
| 22 |
+
claude_3_sonnet_20240229,0.6666666666666666
|
| 23 |
+
llama3_70b_instruct,0.65
|
| 24 |
+
claude_3_haiku_20240307,0.6333333333333333
|
| 25 |
+
gpt_4_0613,0.6166666666666667
|
| 26 |
+
mistral_large_2402,0.6
|
| 27 |
+
mixtral_8x22b_instruct_v0_1,0.5833333333333334
|
| 28 |
+
qwen1_5_72b_chat,0.5666666666666667
|
| 29 |
+
phi_3_medium_4k_instruct,0.55
|
| 30 |
+
command_r_plus,0.5333333333333333
|
| 31 |
+
mistral_medium,0.5166666666666667
|
| 32 |
+
internlm2_5_20b_chat,0.5
|
| 33 |
+
phi_3_small_8k_instruct,0.48333333333333334
|
| 34 |
+
mistral_next,0.4666666666666667
|
| 35 |
+
gpt_3_5_turbo_0613,0.45
|
| 36 |
+
dbrx_instructruct_preview,0.43333333333333335
|
| 37 |
+
internlm2_20b_chat,0.4166666666666667
|
| 38 |
+
claude_2_0,0.4
|
| 39 |
+
mixtral_8x7b_instruct_v0_1,0.38333333333333336
|
| 40 |
+
gpt_3_5_turbo_0125,0.36666666666666664
|
| 41 |
+
yi_34b_chat,0.35
|
| 42 |
+
starling_lm_7b_beta,0.3333333333333333
|
| 43 |
+
claude_2_1,0.31666666666666665
|
| 44 |
+
llama3_1_8b_instruct,0.3
|
| 45 |
+
snorkel_mistral_pairrm_dpo,0.2833333333333333
|
| 46 |
+
llama3_8b_instruct,0.26666666666666666
|
| 47 |
+
gpt_3_5_turbo_1106,0.25
|
| 48 |
+
gpt_3_5_turbo_0301,0.23333333333333334
|
| 49 |
+
gemini_1_0_pro,0.21666666666666667
|
| 50 |
+
snowflake_arctic_instruct,0.2
|
| 51 |
+
command_r,0.18333333333333332
|
| 52 |
+
phi_3_mini_128k_instruct,0.16666666666666666
|
| 53 |
+
tulu_2_dpo_70b,0.15
|
| 54 |
+
starling_lm_7b_alpha,0.13333333333333333
|
| 55 |
+
mistral_7b_instruct,0.11666666666666667
|
| 56 |
+
gemma_1_1_7b_it,0.1
|
| 57 |
+
llama_2_70b_chat,0.08333333333333333
|
| 58 |
+
vicuna_33b_v1_3,0.06666666666666667
|
| 59 |
+
gemma_7b_it,0.05
|
| 60 |
+
llama_2_7b_chat,0.03333333333333333
|
| 61 |
+
gemma_1_1_2b_it,0.016666666666666666
|
| 62 |
+
gemma_2b_it,0.0
|
cache/agreements_cache_741f08262e15cba4bd6c8b25f2b138ca.csv
ADDED
|
@@ -0,0 +1,711 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
scenario,scenario_source,ref_scenario,ref_source,corr_type,model_select_strategy,model_subset_size_requested,exp_n,correlation,p_value
|
| 2 |
+
Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,0,0.2778254199662385,0.2400384567875128
|
| 3 |
+
Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,1,0.40368671387966554,0.08581278065055217
|
| 4 |
+
Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,2,0.42599897728156577,0.07162425926742408
|
| 5 |
+
Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,3,0.2778254199662385,0.2400384567875128
|
| 6 |
+
Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,4,0.36698792170878686,0.11834981273562825
|
| 7 |
+
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,0,-0.018181818181818184,1.0
|
| 8 |
+
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,1,-0.018181818181818184,1.0
|
| 9 |
+
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,2,-0.05454545454545454,0.8792698312489979
|
| 10 |
+
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,3,-0.018181818181818184,1.0
|
| 11 |
+
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,4,-0.1272727272727273,0.6480954385121052
|
| 12 |
+
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,0,0.05454545454545454,0.8792698312489979
|
| 13 |
+
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,1,-0.018181818181818184,1.0
|
| 14 |
+
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,2,-0.018181818181818184,1.0
|
| 15 |
+
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,3,0.05454545454545454,0.8792698312489979
|
| 16 |
+
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,4,-0.05454545454545454,0.8792698312489979
|
| 17 |
+
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,0,0.05454545454545454,0.8792698312489979
|
| 18 |
+
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,1,0.23636363636363636,0.3587114698573032
|
| 19 |
+
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,2,0.2,0.4453821448613115
|
| 20 |
+
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,3,0.05454545454545454,0.8792698312489979
|
| 21 |
+
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,4,0.1272727272727273,0.6480954385121052
|
| 22 |
+
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,0,0.587180674734059,0.01246215829454031
|
| 23 |
+
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,1,0.6727272727272727,0.0031063111271444604
|
| 24 |
+
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,2,0.697277051246695,0.003004262239398284
|
| 25 |
+
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,3,0.587180674734059,0.01246215829454031
|
| 26 |
+
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,4,0.6605782590758164,0.004936818556325077
|
| 27 |
+
Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,0,0.6000000000000001,0.00994553671637005
|
| 28 |
+
Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,1,0.6727272727272727,0.0031063111271444604
|
| 29 |
+
Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,2,0.7090909090909091,0.0015912097162097162
|
| 30 |
+
Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,3,0.6000000000000001,0.00994553671637005
|
| 31 |
+
Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,4,0.6363636363636364,0.005707170915504249
|
| 32 |
+
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,0,0.2727272727272727,0.2829668209876543
|
| 33 |
+
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,1,0.34545454545454546,0.16457331248997917
|
| 34 |
+
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,2,0.38181818181818183,0.12097096961680295
|
| 35 |
+
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,3,0.2727272727272727,0.2829668209876543
|
| 36 |
+
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,4,0.34545454545454546,0.16457331248997917
|
| 37 |
+
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,0,0.6363636363636364,0.005707170915504249
|
| 38 |
+
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,1,0.6727272727272727,0.0031063111271444604
|
| 39 |
+
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,2,0.6363636363636364,0.005707170915504249
|
| 40 |
+
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,3,0.6363636363636364,0.005707170915504249
|
| 41 |
+
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,4,0.7090909090909091,0.0015912097162097162
|
| 42 |
+
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,0,0.18349396085439343,0.43487965849578336
|
| 43 |
+
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,1,0.2935903373670295,0.21152242941072896
|
| 44 |
+
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,2,0.2727272727272727,0.2829668209876543
|
| 45 |
+
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,3,0.18349396085439343,0.43487965849578336
|
| 46 |
+
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,4,0.2568915451961508,0.27429882739587574
|
| 47 |
+
Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,0,0.4909090909090909,0.04053235730319064
|
| 48 |
+
Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,1,0.6000000000000001,0.00994553671637005
|
| 49 |
+
Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,2,0.5636363636363636,0.016540504248837583
|
| 50 |
+
Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,3,0.4909090909090909,0.04053235730319064
|
| 51 |
+
Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,4,0.5636363636363636,0.016540504248837583
|
| 52 |
+
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,0,0.34545454545454546,0.16457331248997917
|
| 53 |
+
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,1,0.41818181818181815,0.08656124739458072
|
| 54 |
+
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,2,0.4909090909090909,0.04053235730319064
|
| 55 |
+
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,3,0.34545454545454546,0.16457331248997917
|
| 56 |
+
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,11,4,0.34545454545454546,0.16457331248997917
|
| 57 |
+
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,11,0,0.9272727272727274,3.2567740901074234e-06
|
| 58 |
+
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,11,1,0.8545454545454545,4.624619207952541e-05
|
| 59 |
+
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,11,2,0.9272727272727274,3.2567740901074234e-06
|
| 60 |
+
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,11,3,0.8545454545454545,4.624619207952541e-05
|
| 61 |
+
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,11,4,0.7818181818181819,0.0003334435626102293
|
| 62 |
+
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,11,0,0.8181818181818182,0.00013227513227513228
|
| 63 |
+
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,11,1,0.8181818181818182,0.00013227513227513228
|
| 64 |
+
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,11,2,1.0,5.010421677088344e-08
|
| 65 |
+
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,11,3,0.6727272727272727,0.0031063111271444604
|
| 66 |
+
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,11,4,0.7454545454545454,0.000759529822029822
|
| 67 |
+
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,11,0,0.45454545454545453,0.06017015392015392
|
| 68 |
+
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,11,1,0.41818181818181815,0.08656124739458072
|
| 69 |
+
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,11,2,0.45454545454545453,0.06017015392015392
|
| 70 |
+
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,11,3,0.7454545454545454,0.000759529822029822
|
| 71 |
+
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,11,4,0.5272727272727272,0.02638447971781305
|
| 72 |
+
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,11,0,0.8181818181818182,0.00013227513227513228
|
| 73 |
+
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,11,1,0.5636363636363636,0.016540504248837583
|
| 74 |
+
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,11,2,0.7454545454545454,0.000759529822029822
|
| 75 |
+
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,11,3,0.7454545454545454,0.000759529822029822
|
| 76 |
+
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,11,4,0.7090909090909091,0.0015912097162097162
|
| 77 |
+
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,11,0,0.8909090909090909,1.3728555395222063e-05
|
| 78 |
+
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,11,1,0.9272727272727274,3.2567740901074234e-06
|
| 79 |
+
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,11,2,1.0,5.010421677088344e-08
|
| 80 |
+
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,11,3,0.8181818181818182,0.00013227513227513228
|
| 81 |
+
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,11,4,0.7818181818181819,0.0003334435626102293
|
| 82 |
+
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,11,0,0.8909090909090909,1.3728555395222063e-05
|
| 83 |
+
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,11,1,0.5272727272727272,0.02638447971781305
|
| 84 |
+
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,11,2,0.8545454545454545,4.624619207952541e-05
|
| 85 |
+
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,11,3,0.4403855060505442,0.06091869077971648
|
| 86 |
+
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,11,4,0.587180674734059,0.01246215829454031
|
| 87 |
+
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,11,0,0.7454545454545454,0.000759529822029822
|
| 88 |
+
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,11,1,0.45454545454545453,0.06017015392015392
|
| 89 |
+
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,11,2,0.38181818181818183,0.12097096961680295
|
| 90 |
+
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,11,3,0.6363636363636364,0.005707170915504249
|
| 91 |
+
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,11,4,0.587180674734059,0.01246215829454031
|
| 92 |
+
Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,11,0,0.7090909090909091,0.0015912097162097162
|
| 93 |
+
Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,11,1,0.7090909090909091,0.0015912097162097162
|
| 94 |
+
Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,11,2,0.7090909090909091,0.0015912097162097162
|
| 95 |
+
Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,11,3,0.7090909090909091,0.0015912097162097162
|
| 96 |
+
Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,11,4,0.7090909090909091,0.0015912097162097162
|
| 97 |
+
LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,11,0,1.0,5.010421677088344e-08
|
| 98 |
+
LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,11,1,1.0,5.010421677088344e-08
|
| 99 |
+
LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,11,2,1.0,5.010421677088344e-08
|
| 100 |
+
LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,11,3,1.0,5.010421677088344e-08
|
| 101 |
+
LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,11,4,1.0,5.010421677088344e-08
|
| 102 |
+
MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,0,0.8545454545454545,4.624619207952541e-05
|
| 103 |
+
MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,1,0.7818181818181819,0.0003334435626102293
|
| 104 |
+
MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,2,0.8181818181818182,0.00013227513227513228
|
| 105 |
+
MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,3,0.8181818181818182,0.00013227513227513228
|
| 106 |
+
MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,4,0.8181818181818182,0.00013227513227513228
|
| 107 |
+
MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,0,0.7818181818181819,0.0003334435626102293
|
| 108 |
+
MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,1,0.7454545454545454,0.000759529822029822
|
| 109 |
+
MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,2,0.7090909090909091,0.0015912097162097162
|
| 110 |
+
MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,3,0.4909090909090909,0.04053235730319064
|
| 111 |
+
MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,4,0.8181818181818182,0.00013227513227513228
|
| 112 |
+
MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,0,0.6238794669049377,0.007931923532795268
|
| 113 |
+
MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,1,0.6605782590758164,0.004936818556325077
|
| 114 |
+
MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,2,0.4403855060505442,0.06091869077971648
|
| 115 |
+
MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,3,0.7090909090909091,0.0015912097162097162
|
| 116 |
+
MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,4,0.697277051246695,0.003004262239398284
|
| 117 |
+
MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,0,0.8545454545454545,4.624619207952541e-05
|
| 118 |
+
MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,1,0.7818181818181819,0.0003334435626102293
|
| 119 |
+
MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,2,0.8181818181818182,0.00013227513227513228
|
| 120 |
+
MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,3,0.7818181818181819,0.0003334435626102293
|
| 121 |
+
MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,4,0.7090909090909091,0.0015912097162097162
|
| 122 |
+
MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,0,0.6238794669049377,0.007931923532795268
|
| 123 |
+
MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,1,0.4403855060505442,0.06091869077971648
|
| 124 |
+
MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,2,0.5636363636363636,0.016540504248837583
|
| 125 |
+
MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,3,0.6363636363636364,0.005707170915504249
|
| 126 |
+
MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,4,0.5636363636363636,0.016540504248837583
|
| 127 |
+
MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,0,0.6000000000000001,0.00994553671637005
|
| 128 |
+
MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,1,0.5636363636363636,0.016540504248837583
|
| 129 |
+
MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,2,0.6000000000000001,0.00994553671637005
|
| 130 |
+
MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,3,0.6000000000000001,0.00994553671637005
|
| 131 |
+
MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,4,0.5636363636363636,0.016540504248837583
|
| 132 |
+
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,0,0.7339758434175737,0.0017872890369872653
|
| 133 |
+
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,1,0.587180674734059,0.01246215829454031
|
| 134 |
+
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,2,0.6482593132545567,0.006117582447622459
|
| 135 |
+
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,3,0.759389481241052,0.0013210471654040124
|
| 136 |
+
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,4,0.759389481241052,0.0013210471654040124
|
| 137 |
+
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,0,0.6363636363636364,0.005707170915504249
|
| 138 |
+
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,1,0.7090909090909091,0.0015912097162097162
|
| 139 |
+
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,2,0.6727272727272727,0.0031063111271444604
|
| 140 |
+
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,3,0.2727272727272727,0.2829668209876543
|
| 141 |
+
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,4,0.5272727272727272,0.02638447971781305
|
| 142 |
+
MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,0,0.38181818181818183,0.12097096961680295
|
| 143 |
+
MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,1,0.4909090909090909,0.04053235730319064
|
| 144 |
+
MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,2,0.38895558795273394,0.10000137830747906
|
| 145 |
+
MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,3,0.38181818181818183,0.12097096961680295
|
| 146 |
+
MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,4,0.697277051246695,0.003004262239398284
|
| 147 |
+
MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,0,0.4909090909090909,0.04053235730319064
|
| 148 |
+
MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,1,0.41818181818181815,0.08656124739458072
|
| 149 |
+
MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,2,0.6000000000000001,0.00994553671637005
|
| 150 |
+
MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,3,0.6000000000000001,0.00994553671637005
|
| 151 |
+
MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,11,4,0.6000000000000001,0.00994553671637005
|
| 152 |
+
AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,11,0,0.8181818181818182,0.00013227513227513228
|
| 153 |
+
AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,11,1,0.8807710121010884,0.00017812930545546289
|
| 154 |
+
AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,11,2,0.8807710121010884,0.00017812930545546289
|
| 155 |
+
AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,11,3,0.8807710121010884,0.00017812930545546289
|
| 156 |
+
AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,11,4,0.8545454545454545,4.624619207952541e-05
|
| 157 |
+
LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,11,0,0.7454545454545454,0.000759529822029822
|
| 158 |
+
LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,11,1,0.8181818181818182,0.00013227513227513228
|
| 159 |
+
LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,11,2,0.8545454545454545,4.624619207952541e-05
|
| 160 |
+
LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,11,3,0.8545454545454545,4.624619207952541e-05
|
| 161 |
+
LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,11,4,0.8545454545454545,4.624619207952541e-05
|
| 162 |
+
LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,11,0,0.4770842982214229,0.042330229121360724
|
| 163 |
+
LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,11,1,0.6727272727272727,0.0031063111271444604
|
| 164 |
+
LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,11,2,0.6605782590758164,0.004936818556325077
|
| 165 |
+
LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,11,3,0.8440722199302099,0.0003281542287518694
|
| 166 |
+
LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,11,4,0.7339758434175737,0.0017872890369872653
|
| 167 |
+
LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,11,0,0.9636363636363636,5.511463844797178e-07
|
| 168 |
+
LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,11,1,0.6727272727272727,0.0031063111271444604
|
| 169 |
+
LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,11,2,0.7818181818181819,0.0003334435626102293
|
| 170 |
+
LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,11,3,0.8545454545454545,4.624619207952541e-05
|
| 171 |
+
LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,11,4,0.7818181818181819,0.0003334435626102293
|
| 172 |
+
LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,11,0,0.7090909090909091,0.0015912097162097162
|
| 173 |
+
LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,11,1,0.7454545454545454,0.000759529822029822
|
| 174 |
+
LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,11,2,0.8181818181818182,0.00013227513227513228
|
| 175 |
+
LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,11,3,0.8909090909090909,1.3728555395222063e-05
|
| 176 |
+
LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,11,4,0.8545454545454545,4.624619207952541e-05
|
| 177 |
+
LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,11,0,0.4909090909090909,0.04053235730319064
|
| 178 |
+
LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,11,1,0.6363636363636364,0.005707170915504249
|
| 179 |
+
LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,11,2,0.7454545454545454,0.000759529822029822
|
| 180 |
+
LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,11,3,0.8545454545454545,4.624619207952541e-05
|
| 181 |
+
LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,11,4,0.7454545454545454,0.000759529822029822
|
| 182 |
+
LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,11,0,0.45454545454545453,0.06017015392015392
|
| 183 |
+
LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,11,1,0.8181818181818182,0.00013227513227513228
|
| 184 |
+
LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,11,2,0.6363636363636364,0.005707170915504249
|
| 185 |
+
LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,11,3,0.9272727272727274,3.2567740901074234e-06
|
| 186 |
+
LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,11,4,0.8545454545454545,4.624619207952541e-05
|
| 187 |
+
LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,11,0,0.6000000000000001,0.00994553671637005
|
| 188 |
+
LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,11,1,0.7090909090909091,0.0015912097162097162
|
| 189 |
+
LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,11,2,0.6727272727272727,0.0031063111271444604
|
| 190 |
+
LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,11,3,0.4909090909090909,0.04053235730319064
|
| 191 |
+
LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,11,4,0.6727272727272727,0.0031063111271444604
|
| 192 |
+
WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,11,0,0.8909090909090909,1.3728555395222063e-05
|
| 193 |
+
WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,11,1,0.8181818181818182,0.00013227513227513228
|
| 194 |
+
WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,11,2,0.8909090909090909,1.3728555395222063e-05
|
| 195 |
+
WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,11,3,0.8909090909090909,1.3728555395222063e-05
|
| 196 |
+
WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,11,4,0.8181818181818182,0.00013227513227513228
|
| 197 |
+
WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,11,0,0.7454545454545454,0.000759529822029822
|
| 198 |
+
WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,11,1,0.8181818181818182,0.00013227513227513228
|
| 199 |
+
WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,11,2,0.8545454545454545,4.624619207952541e-05
|
| 200 |
+
WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,11,3,0.7454545454545454,0.000759529822029822
|
| 201 |
+
WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,11,4,0.7454545454545454,0.000759529822029822
|
| 202 |
+
WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,11,0,0.7454545454545454,0.000759529822029822
|
| 203 |
+
WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,11,1,0.7818181818181819,0.0003334435626102293
|
| 204 |
+
WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,11,2,0.7818181818181819,0.0003334435626102293
|
| 205 |
+
WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,11,3,0.7454545454545454,0.000759529822029822
|
| 206 |
+
WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,11,4,0.7454545454545454,0.000759529822029822
|
| 207 |
+
WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,11,0,1.0,5.010421677088344e-08
|
| 208 |
+
WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,11,1,0.9636363636363636,5.511463844797178e-07
|
| 209 |
+
WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,11,2,0.8909090909090909,1.3728555395222063e-05
|
| 210 |
+
WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,11,3,0.9636363636363636,5.511463844797178e-07
|
| 211 |
+
WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,11,4,1.0,5.010421677088344e-08
|
| 212 |
+
WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,11,0,1.0,5.010421677088344e-08
|
| 213 |
+
WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,11,1,1.0,5.010421677088344e-08
|
| 214 |
+
WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,11,2,0.9272727272727274,3.2567740901074234e-06
|
| 215 |
+
WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,11,3,0.9636363636363636,5.511463844797178e-07
|
| 216 |
+
WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,11,4,1.0,5.010421677088344e-08
|
| 217 |
+
WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,11,0,0.9272727272727274,3.2567740901074234e-06
|
| 218 |
+
WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,11,1,0.9636363636363636,5.511463844797178e-07
|
| 219 |
+
WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,11,2,0.8909090909090909,1.3728555395222063e-05
|
| 220 |
+
WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,11,3,0.8181818181818182,0.00013227513227513228
|
| 221 |
+
WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,11,4,0.9272727272727274,3.2567740901074234e-06
|
| 222 |
+
WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,11,0,0.9636363636363636,5.511463844797178e-07
|
| 223 |
+
WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,11,1,0.9636363636363636,5.511463844797178e-07
|
| 224 |
+
WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,11,2,0.8909090909090909,1.3728555395222063e-05
|
| 225 |
+
WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,11,3,0.8909090909090909,1.3728555395222063e-05
|
| 226 |
+
WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,11,4,0.9636363636363636,5.511463844797178e-07
|
| 227 |
+
Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,11,0,1.0,5.010421677088344e-08
|
| 228 |
+
Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,11,1,1.0,5.010421677088344e-08
|
| 229 |
+
Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,11,2,1.0,5.010421677088344e-08
|
| 230 |
+
Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,11,3,1.0,5.010421677088344e-08
|
| 231 |
+
Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,11,4,1.0,5.010421677088344e-08
|
| 232 |
+
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,11,0,0.45454545454545453,0.06017015392015392
|
| 233 |
+
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,11,1,0.6000000000000001,0.00994553671637005
|
| 234 |
+
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,11,2,0.3090909090909091,0.21834651074234407
|
| 235 |
+
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,11,3,0.5272727272727272,0.02638447971781305
|
| 236 |
+
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,11,4,0.38181818181818183,0.12097096961680295
|
| 237 |
+
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,11,0,0.6000000000000001,0.00994553671637005
|
| 238 |
+
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,11,1,0.5636363636363636,0.016540504248837583
|
| 239 |
+
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,11,2,0.5272727272727272,0.02638447971781305
|
| 240 |
+
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,11,3,0.6000000000000001,0.00994553671637005
|
| 241 |
+
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,11,4,0.4909090909090909,0.04053235730319064
|
| 242 |
+
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,11,0,0.45454545454545453,0.06017015392015392
|
| 243 |
+
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,11,1,0.6000000000000001,0.00994553671637005
|
| 244 |
+
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,11,2,0.34545454545454546,0.16457331248997917
|
| 245 |
+
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,11,3,0.41818181818181815,0.08656124739458072
|
| 246 |
+
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,11,4,0.2727272727272727,0.2829668209876543
|
| 247 |
+
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,11,0,0.5741725345968929,0.015177848122929492
|
| 248 |
+
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,11,1,0.3519121986239021,0.1366995137219537
|
| 249 |
+
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,11,2,0.42599897728156577,0.07162425926742408
|
| 250 |
+
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,11,3,0.38181818181818183,0.12097096961680295
|
| 251 |
+
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,11,4,0.4403855060505442,0.06091869077971648
|
| 252 |
+
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,11,0,0.7090909090909091,0.0015912097162097162
|
| 253 |
+
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,11,1,0.7818181818181819,0.0003334435626102293
|
| 254 |
+
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,11,2,0.6727272727272727,0.0031063111271444604
|
| 255 |
+
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,11,3,0.7454545454545454,0.000759529822029822
|
| 256 |
+
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,11,4,0.6727272727272727,0.0031063111271444604
|
| 257 |
+
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,11,0,0.6000000000000001,0.00994553671637005
|
| 258 |
+
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,11,1,0.5272727272727272,0.02638447971781305
|
| 259 |
+
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,11,2,0.3090909090909091,0.21834651074234407
|
| 260 |
+
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,11,3,0.45454545454545453,0.06017015392015392
|
| 261 |
+
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,11,4,0.2727272727272727,0.2829668209876543
|
| 262 |
+
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,11,0,0.4403855060505442,0.06091869077971648
|
| 263 |
+
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,11,1,0.38181818181818183,0.12097096961680295
|
| 264 |
+
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,11,2,0.4403855060505442,0.06091869077971648
|
| 265 |
+
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,11,3,0.45454545454545453,0.06017015392015392
|
| 266 |
+
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,11,4,0.36698792170878686,0.11834981273562825
|
| 267 |
+
BFCL,bfcl_240906.csv,aggregate,aggregate,kendall,random,11,0,0.2,0.4453821448613115
|
| 268 |
+
BFCL,bfcl_240906.csv,aggregate,aggregate,kendall,random,11,1,0.38181818181818183,0.12097096961680295
|
| 269 |
+
BFCL,bfcl_240906.csv,aggregate,aggregate,kendall,random,11,2,0.41818181818181815,0.08656124739458072
|
| 270 |
+
BFCL,bfcl_240906.csv,aggregate,aggregate,kendall,random,11,3,0.5272727272727272,0.02638447971781305
|
| 271 |
+
BFCL,bfcl_240906.csv,aggregate,aggregate,kendall,random,11,4,0.5272727272727272,0.02638447971781305
|
| 272 |
+
BIGGEN,biggen_240829.csv,aggregate,aggregate,kendall,random,11,0,0.8181818181818182,0.00013227513227513228
|
| 273 |
+
BIGGEN,biggen_240829.csv,aggregate,aggregate,kendall,random,11,1,0.8181818181818182,0.00013227513227513228
|
| 274 |
+
BIGGEN,biggen_240829.csv,aggregate,aggregate,kendall,random,11,2,0.8909090909090909,1.3728555395222063e-05
|
| 275 |
+
BIGGEN,biggen_240829.csv,aggregate,aggregate,kendall,random,11,3,0.8181818181818182,0.00013227513227513228
|
| 276 |
+
BIGGEN,biggen_240829.csv,aggregate,aggregate,kendall,random,11,4,0.7090909090909091,0.0015912097162097162
|
| 277 |
+
BIGGEN Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,11,0,0.7454545454545454,0.000759529822029822
|
| 278 |
+
BIGGEN Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,11,1,0.7818181818181819,0.0003334435626102293
|
| 279 |
+
BIGGEN Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,11,2,0.8181818181818182,0.00013227513227513228
|
| 280 |
+
BIGGEN Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,11,3,0.8073734277593311,0.0005907573118657002
|
| 281 |
+
BIGGEN Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,11,4,0.7454545454545454,0.000759529822029822
|
| 282 |
+
BIGGEN Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,11,0,0.587180674734059,0.01246215829454031
|
| 283 |
+
BIGGEN Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,11,1,0.6482593132545567,0.006117582447622459
|
| 284 |
+
BIGGEN Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,11,2,0.8545454545454545,4.624619207952541e-05
|
| 285 |
+
BIGGEN Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,11,3,0.7706746355884524,0.0010393630991335228
|
| 286 |
+
BIGGEN Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,11,4,0.5371291452680612,0.02311942970946668
|
| 287 |
+
BIGGEN Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,11,0,0.6238794669049377,0.007931923532795268
|
| 288 |
+
BIGGEN Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,11,1,0.4909090909090909,0.04053235730319064
|
| 289 |
+
BIGGEN Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,11,2,0.8440722199302099,0.0003281542287518694
|
| 290 |
+
BIGGEN Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,11,3,0.7454545454545454,0.000759529822029822
|
| 291 |
+
BIGGEN Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,11,4,0.36698792170878686,0.11834981273562825
|
| 292 |
+
BIGGEN Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,11,0,0.8909090909090909,1.3728555395222063e-05
|
| 293 |
+
BIGGEN Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,11,1,0.9272727272727274,3.2567740901074234e-06
|
| 294 |
+
BIGGEN Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,11,2,1.0,5.010421677088344e-08
|
| 295 |
+
BIGGEN Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,11,3,0.7090909090909091,0.0015912097162097162
|
| 296 |
+
BIGGEN Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,11,4,0.6727272727272727,0.0031063111271444604
|
| 297 |
+
BIGGEN Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,11,0,0.8181818181818182,0.00013227513227513228
|
| 298 |
+
BIGGEN Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,11,1,0.8073734277593311,0.0005907573118657002
|
| 299 |
+
BIGGEN Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,11,2,0.8909090909090909,1.3728555395222063e-05
|
| 300 |
+
BIGGEN Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,11,3,0.7818181818181819,0.0003334435626102293
|
| 301 |
+
BIGGEN Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,11,4,0.6605782590758164,0.004936818556325077
|
| 302 |
+
BIGGEN Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,11,0,-0.0909090909090909,0.7611503928170594
|
| 303 |
+
BIGGEN Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,11,1,0.07339758434175737,0.7547764265871044
|
| 304 |
+
BIGGEN Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,11,2,0.4403855060505442,0.06091869077971648
|
| 305 |
+
BIGGEN Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,11,3,0.3302891295379082,0.15985367483762747
|
| 306 |
+
BIGGEN Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,11,4,0.1272727272727273,0.6480954385121052
|
| 307 |
+
BIGGEN Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,11,0,0.7090909090909091,0.0015912097162097162
|
| 308 |
+
BIGGEN Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,11,1,0.7818181818181819,0.0003334435626102293
|
| 309 |
+
BIGGEN Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,11,2,0.8705196492275474,0.00023202582506637044
|
| 310 |
+
BIGGEN Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,11,3,0.7479575920067658,0.001637274718449882
|
| 311 |
+
BIGGEN Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,11,4,0.5983660736054126,0.01175728488671479
|
| 312 |
+
BIGGEN Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,11,0,0.7090909090909091,0.0015912097162097162
|
| 313 |
+
BIGGEN Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,11,1,0.6000000000000001,0.00994553671637005
|
| 314 |
+
BIGGEN Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,11,2,0.7090909090909091,0.0015912097162097162
|
| 315 |
+
BIGGEN Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,11,3,0.7454545454545454,0.000759529822029822
|
| 316 |
+
BIGGEN Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,11,4,0.5272727272727272,0.02638447971781305
|
| 317 |
+
BIGGEN Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,11,0,0.7706746355884524,0.0010393630991335228
|
| 318 |
+
BIGGEN Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,11,1,0.8909090909090909,1.3728555395222063e-05
|
| 319 |
+
BIGGEN Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,11,2,0.5272727272727272,0.02638447971781305
|
| 320 |
+
BIGGEN Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,11,3,0.7454545454545454,0.000759529822029822
|
| 321 |
+
BIGGEN Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,11,4,0.7818181818181819,0.0003334435626102293
|
| 322 |
+
LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,11,0,0.7818181818181819,0.0003334435626102293
|
| 323 |
+
LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,11,1,0.8545454545454545,4.624619207952541e-05
|
| 324 |
+
LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,11,2,0.7818181818181819,0.0003334435626102293
|
| 325 |
+
LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,11,3,0.8545454545454545,4.624619207952541e-05
|
| 326 |
+
LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,11,4,0.7818181818181819,0.0003334435626102293
|
| 327 |
+
LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,11,0,0.6731618328060892,0.004677734981047257
|
| 328 |
+
LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,11,1,0.759389481241052,0.0013210471654040124
|
| 329 |
+
LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,11,2,0.7339758434175737,0.0017872890369872653
|
| 330 |
+
LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,11,3,0.6238794669049377,0.007931923532795268
|
| 331 |
+
LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,11,4,0.7090909090909091,0.0015912097162097162
|
| 332 |
+
LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,11,0,0.6363636363636364,0.005707170915504249
|
| 333 |
+
LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,11,1,0.7454545454545454,0.000759529822029822
|
| 334 |
+
LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,11,2,0.7706746355884524,0.0010393630991335228
|
| 335 |
+
LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,11,3,0.8181818181818182,0.00013227513227513228
|
| 336 |
+
LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,11,4,0.7706746355884524,0.0010393630991335228
|
| 337 |
+
LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,11,0,0.7090909090909091,0.0015912097162097162
|
| 338 |
+
LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,11,1,0.8909090909090909,1.3728555395222063e-05
|
| 339 |
+
LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,11,2,0.7818181818181819,0.0003334435626102293
|
| 340 |
+
LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,11,3,0.8545454545454545,4.624619207952541e-05
|
| 341 |
+
LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,11,4,0.8545454545454545,4.624619207952541e-05
|
| 342 |
+
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,11,0,0.5636363636363636,0.016540504248837583
|
| 343 |
+
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,11,1,0.7454545454545454,0.000759529822029822
|
| 344 |
+
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,11,2,0.6363636363636364,0.005707170915504249
|
| 345 |
+
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,11,3,0.7818181818181819,0.0003334435626102293
|
| 346 |
+
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,11,4,0.6363636363636364,0.005707170915504249
|
| 347 |
+
LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,11,0,0.7090909090909091,0.0015912097162097162
|
| 348 |
+
LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,11,1,0.8181818181818182,0.00013227513227513228
|
| 349 |
+
LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,11,2,0.5636363636363636,0.016540504248837583
|
| 350 |
+
LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,11,3,0.8545454545454545,4.624619207952541e-05
|
| 351 |
+
LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,11,4,0.7454545454545454,0.000759529822029822
|
| 352 |
+
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,11,0,0.6727272727272727,0.0031063111271444604
|
| 353 |
+
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,11,1,0.7454545454545454,0.000759529822029822
|
| 354 |
+
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,11,2,0.7090909090909091,0.0015912097162097162
|
| 355 |
+
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,11,3,0.6000000000000001,0.00994553671637005
|
| 356 |
+
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,11,4,0.7454545454545454,0.000759529822029822
|
| 357 |
+
aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,11,0,0.2778254199662385,0.2400384567875128
|
| 358 |
+
aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,11,1,0.40368671387966554,0.08581278065055217
|
| 359 |
+
aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,11,2,0.42599897728156577,0.07162425926742408
|
| 360 |
+
aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,11,3,0.2778254199662385,0.2400384567875128
|
| 361 |
+
aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,11,4,0.36698792170878686,0.11834981273562825
|
| 362 |
+
aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,11,0,-0.018181818181818184,1.0
|
| 363 |
+
aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,11,1,-0.018181818181818184,1.0
|
| 364 |
+
aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,11,2,-0.05454545454545454,0.8792698312489979
|
| 365 |
+
aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,11,3,-0.018181818181818184,1.0
|
| 366 |
+
aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,11,4,-0.1272727272727273,0.6480954385121052
|
| 367 |
+
aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,11,0,0.05454545454545454,0.8792698312489979
|
| 368 |
+
aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,11,1,-0.018181818181818184,1.0
|
| 369 |
+
aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,11,2,-0.018181818181818184,1.0
|
| 370 |
+
aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,11,3,0.05454545454545454,0.8792698312489979
|
| 371 |
+
aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,11,4,-0.05454545454545454,0.8792698312489979
|
| 372 |
+
aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,11,0,0.05454545454545454,0.8792698312489979
|
| 373 |
+
aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,11,1,0.23636363636363636,0.3587114698573032
|
| 374 |
+
aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,11,2,0.2,0.4453821448613115
|
| 375 |
+
aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,11,3,0.05454545454545454,0.8792698312489979
|
| 376 |
+
aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,11,4,0.1272727272727273,0.6480954385121052
|
| 377 |
+
aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,11,0,0.587180674734059,0.01246215829454031
|
| 378 |
+
aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,11,1,0.6727272727272727,0.0031063111271444604
|
| 379 |
+
aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,11,2,0.697277051246695,0.003004262239398284
|
| 380 |
+
aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,11,3,0.587180674734059,0.01246215829454031
|
| 381 |
+
aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,11,4,0.6605782590758164,0.004936818556325077
|
| 382 |
+
aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,11,0,0.6000000000000001,0.00994553671637005
|
| 383 |
+
aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,11,1,0.6727272727272727,0.0031063111271444604
|
| 384 |
+
aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,11,2,0.7090909090909091,0.0015912097162097162
|
| 385 |
+
aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,11,3,0.6000000000000001,0.00994553671637005
|
| 386 |
+
aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,11,4,0.6363636363636364,0.005707170915504249
|
| 387 |
+
aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,11,0,0.2727272727272727,0.2829668209876543
|
| 388 |
+
aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,11,1,0.34545454545454546,0.16457331248997917
|
| 389 |
+
aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,11,2,0.38181818181818183,0.12097096961680295
|
| 390 |
+
aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,11,3,0.2727272727272727,0.2829668209876543
|
| 391 |
+
aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,11,4,0.34545454545454546,0.16457331248997917
|
| 392 |
+
aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,11,0,0.6363636363636364,0.005707170915504249
|
| 393 |
+
aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,11,1,0.6727272727272727,0.0031063111271444604
|
| 394 |
+
aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,11,2,0.6363636363636364,0.005707170915504249
|
| 395 |
+
aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,11,3,0.6363636363636364,0.005707170915504249
|
| 396 |
+
aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,11,4,0.7090909090909091,0.0015912097162097162
|
| 397 |
+
aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,11,0,0.18349396085439343,0.43487965849578336
|
| 398 |
+
aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,11,1,0.2935903373670295,0.21152242941072896
|
| 399 |
+
aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,11,2,0.2727272727272727,0.2829668209876543
|
| 400 |
+
aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,11,3,0.18349396085439343,0.43487965849578336
|
| 401 |
+
aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,11,4,0.2568915451961508,0.27429882739587574
|
| 402 |
+
aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,11,0,0.4909090909090909,0.04053235730319064
|
| 403 |
+
aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,11,1,0.6000000000000001,0.00994553671637005
|
| 404 |
+
aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,11,2,0.5636363636363636,0.016540504248837583
|
| 405 |
+
aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,11,3,0.4909090909090909,0.04053235730319064
|
| 406 |
+
aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,11,4,0.5636363636363636,0.016540504248837583
|
| 407 |
+
aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,11,0,0.34545454545454546,0.16457331248997917
|
| 408 |
+
aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,11,1,0.41818181818181815,0.08656124739458072
|
| 409 |
+
aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,11,2,0.4909090909090909,0.04053235730319064
|
| 410 |
+
aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,11,3,0.34545454545454546,0.16457331248997917
|
| 411 |
+
aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,11,4,0.34545454545454546,0.16457331248997917
|
| 412 |
+
aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,11,0,0.9272727272727274,3.2567740901074234e-06
|
| 413 |
+
aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,11,1,0.8545454545454545,4.624619207952541e-05
|
| 414 |
+
aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,11,2,0.9272727272727274,3.2567740901074234e-06
|
| 415 |
+
aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,11,3,0.8545454545454545,4.624619207952541e-05
|
| 416 |
+
aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,11,4,0.7818181818181819,0.0003334435626102293
|
| 417 |
+
aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,11,0,0.8181818181818182,0.00013227513227513228
|
| 418 |
+
aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,11,1,0.8181818181818182,0.00013227513227513228
|
| 419 |
+
aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,11,2,1.0,5.010421677088344e-08
|
| 420 |
+
aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,11,3,0.6727272727272727,0.0031063111271444604
|
| 421 |
+
aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,11,4,0.7454545454545454,0.000759529822029822
|
| 422 |
+
aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,11,0,0.45454545454545453,0.06017015392015392
|
| 423 |
+
aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,11,1,0.41818181818181815,0.08656124739458072
|
| 424 |
+
aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,11,2,0.45454545454545453,0.06017015392015392
|
| 425 |
+
aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,11,3,0.7454545454545454,0.000759529822029822
|
| 426 |
+
aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,11,4,0.5272727272727272,0.02638447971781305
|
| 427 |
+
aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,11,0,0.8181818181818182,0.00013227513227513228
|
| 428 |
+
aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,11,1,0.5636363636363636,0.016540504248837583
|
| 429 |
+
aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,11,2,0.7454545454545454,0.000759529822029822
|
| 430 |
+
aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,11,3,0.7454545454545454,0.000759529822029822
|
| 431 |
+
aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,11,4,0.7090909090909091,0.0015912097162097162
|
| 432 |
+
aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,11,0,0.8909090909090909,1.3728555395222063e-05
|
| 433 |
+
aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,11,1,0.9272727272727274,3.2567740901074234e-06
|
| 434 |
+
aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,11,2,1.0,5.010421677088344e-08
|
| 435 |
+
aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,11,3,0.8181818181818182,0.00013227513227513228
|
| 436 |
+
aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,11,4,0.7818181818181819,0.0003334435626102293
|
| 437 |
+
aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,11,0,0.8909090909090909,1.3728555395222063e-05
|
| 438 |
+
aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,11,1,0.5272727272727272,0.02638447971781305
|
| 439 |
+
aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,11,2,0.8545454545454545,4.624619207952541e-05
|
| 440 |
+
aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,11,3,0.4403855060505442,0.06091869077971648
|
| 441 |
+
aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,11,4,0.587180674734059,0.01246215829454031
|
| 442 |
+
aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,11,0,0.7454545454545454,0.000759529822029822
|
| 443 |
+
aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,11,1,0.45454545454545453,0.06017015392015392
|
| 444 |
+
aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,11,2,0.38181818181818183,0.12097096961680295
|
| 445 |
+
aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,11,3,0.6363636363636364,0.005707170915504249
|
| 446 |
+
aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,11,4,0.587180674734059,0.01246215829454031
|
| 447 |
+
aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,11,0,0.7090909090909091,0.0015912097162097162
|
| 448 |
+
aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,11,1,0.7090909090909091,0.0015912097162097162
|
| 449 |
+
aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,11,2,0.7090909090909091,0.0015912097162097162
|
| 450 |
+
aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,11,3,0.7090909090909091,0.0015912097162097162
|
| 451 |
+
aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,11,4,0.7090909090909091,0.0015912097162097162
|
| 452 |
+
aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,11,0,1.0,5.010421677088344e-08
|
| 453 |
+
aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,11,1,1.0,5.010421677088344e-08
|
| 454 |
+
aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,11,2,1.0,5.010421677088344e-08
|
| 455 |
+
aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,11,3,1.0,5.010421677088344e-08
|
| 456 |
+
aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,11,4,1.0,5.010421677088344e-08
|
| 457 |
+
aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,11,0,0.8545454545454545,4.624619207952541e-05
|
| 458 |
+
aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,11,1,0.7818181818181819,0.0003334435626102293
|
| 459 |
+
aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,11,2,0.8181818181818182,0.00013227513227513228
|
| 460 |
+
aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,11,3,0.8181818181818182,0.00013227513227513228
|
| 461 |
+
aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,11,4,0.8181818181818182,0.00013227513227513228
|
| 462 |
+
aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,11,0,0.7818181818181819,0.0003334435626102293
|
| 463 |
+
aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,11,1,0.7454545454545454,0.000759529822029822
|
| 464 |
+
aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,11,2,0.7090909090909091,0.0015912097162097162
|
| 465 |
+
aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,11,3,0.4909090909090909,0.04053235730319064
|
| 466 |
+
aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,11,4,0.8181818181818182,0.00013227513227513228
|
| 467 |
+
aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,11,0,0.6238794669049377,0.007931923532795268
|
| 468 |
+
aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,11,1,0.6605782590758164,0.004936818556325077
|
| 469 |
+
aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,11,2,0.4403855060505442,0.06091869077971648
|
| 470 |
+
aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,11,3,0.7090909090909091,0.0015912097162097162
|
| 471 |
+
aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,11,4,0.697277051246695,0.003004262239398284
|
| 472 |
+
aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,11,0,0.8545454545454545,4.624619207952541e-05
|
| 473 |
+
aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,11,1,0.7818181818181819,0.0003334435626102293
|
| 474 |
+
aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,11,2,0.8181818181818182,0.00013227513227513228
|
| 475 |
+
aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,11,3,0.7818181818181819,0.0003334435626102293
|
| 476 |
+
aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,11,4,0.7090909090909091,0.0015912097162097162
|
| 477 |
+
aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,11,0,0.6238794669049377,0.007931923532795268
|
| 478 |
+
aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,11,1,0.4403855060505442,0.06091869077971648
|
| 479 |
+
aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,11,2,0.5636363636363636,0.016540504248837583
|
| 480 |
+
aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,11,3,0.6363636363636364,0.005707170915504249
|
| 481 |
+
aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,11,4,0.5636363636363636,0.016540504248837583
|
| 482 |
+
aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,11,0,0.6000000000000001,0.00994553671637005
|
| 483 |
+
aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,11,1,0.5636363636363636,0.016540504248837583
|
| 484 |
+
aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,11,2,0.6000000000000001,0.00994553671637005
|
| 485 |
+
aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,11,3,0.6000000000000001,0.00994553671637005
|
| 486 |
+
aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,11,4,0.5636363636363636,0.016540504248837583
|
| 487 |
+
aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,11,0,0.7339758434175737,0.0017872890369872653
|
| 488 |
+
aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,11,1,0.587180674734059,0.01246215829454031
|
| 489 |
+
aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,11,2,0.6482593132545567,0.006117582447622459
|
| 490 |
+
aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,11,3,0.759389481241052,0.0013210471654040124
|
| 491 |
+
aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,11,4,0.759389481241052,0.0013210471654040124
|
| 492 |
+
aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,11,0,0.6363636363636364,0.005707170915504249
|
| 493 |
+
aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,11,1,0.7090909090909091,0.0015912097162097162
|
| 494 |
+
aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,11,2,0.6727272727272727,0.0031063111271444604
|
| 495 |
+
aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,11,3,0.2727272727272727,0.2829668209876543
|
| 496 |
+
aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,11,4,0.5272727272727272,0.02638447971781305
|
| 497 |
+
aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,11,0,0.38181818181818183,0.12097096961680295
|
| 498 |
+
aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,11,1,0.4909090909090909,0.04053235730319064
|
| 499 |
+
aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,11,2,0.38895558795273394,0.10000137830747906
|
| 500 |
+
aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,11,3,0.38181818181818183,0.12097096961680295
|
| 501 |
+
aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,11,4,0.697277051246695,0.003004262239398284
|
| 502 |
+
aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,11,0,0.4909090909090909,0.04053235730319064
|
| 503 |
+
aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,11,1,0.41818181818181815,0.08656124739458072
|
| 504 |
+
aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,11,2,0.6000000000000001,0.00994553671637005
|
| 505 |
+
aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,11,3,0.6000000000000001,0.00994553671637005
|
| 506 |
+
aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,11,4,0.6000000000000001,0.00994553671637005
|
| 507 |
+
aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,11,0,0.8181818181818182,0.00013227513227513228
|
| 508 |
+
aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,11,1,0.8807710121010884,0.00017812930545546289
|
| 509 |
+
aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,11,2,0.8807710121010884,0.00017812930545546289
|
| 510 |
+
aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,11,3,0.8807710121010884,0.00017812930545546289
|
| 511 |
+
aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,11,4,0.8545454545454545,4.624619207952541e-05
|
| 512 |
+
aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,11,0,0.7454545454545454,0.000759529822029822
|
| 513 |
+
aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,11,1,0.8181818181818182,0.00013227513227513228
|
| 514 |
+
aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,11,2,0.8545454545454545,4.624619207952541e-05
|
| 515 |
+
aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,11,3,0.8545454545454545,4.624619207952541e-05
|
| 516 |
+
aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,11,4,0.8545454545454545,4.624619207952541e-05
|
| 517 |
+
aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,11,0,0.4770842982214229,0.042330229121360724
|
| 518 |
+
aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,11,1,0.6727272727272727,0.0031063111271444604
|
| 519 |
+
aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,11,2,0.6605782590758164,0.004936818556325077
|
| 520 |
+
aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,11,3,0.8440722199302099,0.0003281542287518694
|
| 521 |
+
aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,11,4,0.7339758434175737,0.0017872890369872653
|
| 522 |
+
aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,11,0,0.9636363636363636,5.511463844797178e-07
|
| 523 |
+
aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,11,1,0.6727272727272727,0.0031063111271444604
|
| 524 |
+
aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,11,2,0.7818181818181819,0.0003334435626102293
|
| 525 |
+
aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,11,3,0.8545454545454545,4.624619207952541e-05
|
| 526 |
+
aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,11,4,0.7818181818181819,0.0003334435626102293
|
| 527 |
+
aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,11,0,0.7090909090909091,0.0015912097162097162
|
| 528 |
+
aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,11,1,0.7454545454545454,0.000759529822029822
|
| 529 |
+
aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,11,2,0.8181818181818182,0.00013227513227513228
|
| 530 |
+
aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,11,3,0.8909090909090909,1.3728555395222063e-05
|
| 531 |
+
aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,11,4,0.8545454545454545,4.624619207952541e-05
|
| 532 |
+
aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,11,0,0.4909090909090909,0.04053235730319064
|
| 533 |
+
aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,11,1,0.6363636363636364,0.005707170915504249
|
| 534 |
+
aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,11,2,0.7454545454545454,0.000759529822029822
|
| 535 |
+
aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,11,3,0.8545454545454545,4.624619207952541e-05
|
| 536 |
+
aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,11,4,0.7454545454545454,0.000759529822029822
|
| 537 |
+
aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,11,0,0.45454545454545453,0.06017015392015392
|
| 538 |
+
aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,11,1,0.8181818181818182,0.00013227513227513228
|
| 539 |
+
aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,11,2,0.6363636363636364,0.005707170915504249
|
| 540 |
+
aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,11,3,0.9272727272727274,3.2567740901074234e-06
|
| 541 |
+
aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,11,4,0.8545454545454545,4.624619207952541e-05
|
| 542 |
+
aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,11,0,0.6000000000000001,0.00994553671637005
|
| 543 |
+
aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,11,1,0.7090909090909091,0.0015912097162097162
|
| 544 |
+
aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,11,2,0.6727272727272727,0.0031063111271444604
|
| 545 |
+
aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,11,3,0.4909090909090909,0.04053235730319064
|
| 546 |
+
aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,11,4,0.6727272727272727,0.0031063111271444604
|
| 547 |
+
aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,11,0,0.8909090909090909,1.3728555395222063e-05
|
| 548 |
+
aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,11,1,0.8181818181818182,0.00013227513227513228
|
| 549 |
+
aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,11,2,0.8909090909090909,1.3728555395222063e-05
|
| 550 |
+
aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,11,3,0.8909090909090909,1.3728555395222063e-05
|
| 551 |
+
aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,11,4,0.8181818181818182,0.00013227513227513228
|
| 552 |
+
aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,11,0,0.7454545454545454,0.000759529822029822
|
| 553 |
+
aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,11,1,0.8181818181818182,0.00013227513227513228
|
| 554 |
+
aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,11,2,0.8545454545454545,4.624619207952541e-05
|
| 555 |
+
aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,11,3,0.7454545454545454,0.000759529822029822
|
| 556 |
+
aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,11,4,0.7454545454545454,0.000759529822029822
|
| 557 |
+
aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,11,0,0.7454545454545454,0.000759529822029822
|
| 558 |
+
aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,11,1,0.7818181818181819,0.0003334435626102293
|
| 559 |
+
aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,11,2,0.7818181818181819,0.0003334435626102293
|
| 560 |
+
aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,11,3,0.7454545454545454,0.000759529822029822
|
| 561 |
+
aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,11,4,0.7454545454545454,0.000759529822029822
|
| 562 |
+
aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,11,0,1.0,5.010421677088344e-08
|
| 563 |
+
aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,11,1,0.9636363636363636,5.511463844797178e-07
|
| 564 |
+
aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,11,2,0.8909090909090909,1.3728555395222063e-05
|
| 565 |
+
aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,11,3,0.9636363636363636,5.511463844797178e-07
|
| 566 |
+
aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,11,4,1.0,5.010421677088344e-08
|
| 567 |
+
aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,11,0,1.0,5.010421677088344e-08
|
| 568 |
+
aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,11,1,1.0,5.010421677088344e-08
|
| 569 |
+
aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,11,2,0.9272727272727274,3.2567740901074234e-06
|
| 570 |
+
aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,11,3,0.9636363636363636,5.511463844797178e-07
|
| 571 |
+
aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,11,4,1.0,5.010421677088344e-08
|
| 572 |
+
aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,11,0,0.9272727272727274,3.2567740901074234e-06
|
| 573 |
+
aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,11,1,0.9636363636363636,5.511463844797178e-07
|
| 574 |
+
aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,11,2,0.8909090909090909,1.3728555395222063e-05
|
| 575 |
+
aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,11,3,0.8181818181818182,0.00013227513227513228
|
| 576 |
+
aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,11,4,0.9272727272727274,3.2567740901074234e-06
|
| 577 |
+
aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,11,0,0.9636363636363636,5.511463844797178e-07
|
| 578 |
+
aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,11,1,0.9636363636363636,5.511463844797178e-07
|
| 579 |
+
aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,11,2,0.8909090909090909,1.3728555395222063e-05
|
| 580 |
+
aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,11,3,0.8909090909090909,1.3728555395222063e-05
|
| 581 |
+
aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,11,4,0.9636363636363636,5.511463844797178e-07
|
| 582 |
+
aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,11,0,1.0,5.010421677088344e-08
|
| 583 |
+
aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,11,1,1.0,5.010421677088344e-08
|
| 584 |
+
aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,11,2,1.0,5.010421677088344e-08
|
| 585 |
+
aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,11,3,1.0,5.010421677088344e-08
|
| 586 |
+
aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,11,4,1.0,5.010421677088344e-08
|
| 587 |
+
aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,11,0,0.45454545454545453,0.06017015392015392
|
| 588 |
+
aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,11,1,0.6000000000000001,0.00994553671637005
|
| 589 |
+
aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,11,2,0.3090909090909091,0.21834651074234407
|
| 590 |
+
aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,11,3,0.5272727272727272,0.02638447971781305
|
| 591 |
+
aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,11,4,0.38181818181818183,0.12097096961680295
|
| 592 |
+
aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,11,0,0.6000000000000001,0.00994553671637005
|
| 593 |
+
aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,11,1,0.5636363636363636,0.016540504248837583
|
| 594 |
+
aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,11,2,0.5272727272727272,0.02638447971781305
|
| 595 |
+
aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,11,3,0.6000000000000001,0.00994553671637005
|
| 596 |
+
aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,11,4,0.4909090909090909,0.04053235730319064
|
| 597 |
+
aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,11,0,0.45454545454545453,0.06017015392015392
|
| 598 |
+
aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,11,1,0.6000000000000001,0.00994553671637005
|
| 599 |
+
aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,11,2,0.34545454545454546,0.16457331248997917
|
| 600 |
+
aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,11,3,0.41818181818181815,0.08656124739458072
|
| 601 |
+
aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,11,4,0.2727272727272727,0.2829668209876543
|
| 602 |
+
aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,11,0,0.5741725345968929,0.015177848122929492
|
| 603 |
+
aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,11,1,0.3519121986239021,0.1366995137219537
|
| 604 |
+
aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,11,2,0.42599897728156577,0.07162425926742408
|
| 605 |
+
aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,11,3,0.38181818181818183,0.12097096961680295
|
| 606 |
+
aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,11,4,0.4403855060505442,0.06091869077971648
|
| 607 |
+
aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,11,0,0.7090909090909091,0.0015912097162097162
|
| 608 |
+
aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,11,1,0.7818181818181819,0.0003334435626102293
|
| 609 |
+
aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,11,2,0.6727272727272727,0.0031063111271444604
|
| 610 |
+
aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,11,3,0.7454545454545454,0.000759529822029822
|
| 611 |
+
aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,11,4,0.6727272727272727,0.0031063111271444604
|
| 612 |
+
aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,11,0,0.6000000000000001,0.00994553671637005
|
| 613 |
+
aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,11,1,0.5272727272727272,0.02638447971781305
|
| 614 |
+
aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,11,2,0.3090909090909091,0.21834651074234407
|
| 615 |
+
aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,11,3,0.45454545454545453,0.06017015392015392
|
| 616 |
+
aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,11,4,0.2727272727272727,0.2829668209876543
|
| 617 |
+
aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,11,0,0.4403855060505442,0.06091869077971648
|
| 618 |
+
aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,11,1,0.38181818181818183,0.12097096961680295
|
| 619 |
+
aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,11,2,0.4403855060505442,0.06091869077971648
|
| 620 |
+
aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,11,3,0.45454545454545453,0.06017015392015392
|
| 621 |
+
aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,11,4,0.36698792170878686,0.11834981273562825
|
| 622 |
+
aggregate,aggregate,BFCL,bfcl_240906.csv,kendall,random,11,0,0.2,0.4453821448613115
|
| 623 |
+
aggregate,aggregate,BFCL,bfcl_240906.csv,kendall,random,11,1,0.38181818181818183,0.12097096961680295
|
| 624 |
+
aggregate,aggregate,BFCL,bfcl_240906.csv,kendall,random,11,2,0.41818181818181815,0.08656124739458072
|
| 625 |
+
aggregate,aggregate,BFCL,bfcl_240906.csv,kendall,random,11,3,0.5272727272727272,0.02638447971781305
|
| 626 |
+
aggregate,aggregate,BFCL,bfcl_240906.csv,kendall,random,11,4,0.5272727272727272,0.02638447971781305
|
| 627 |
+
aggregate,aggregate,BIGGEN,biggen_240829.csv,kendall,random,11,0,0.8181818181818182,0.00013227513227513228
|
| 628 |
+
aggregate,aggregate,BIGGEN,biggen_240829.csv,kendall,random,11,1,0.8181818181818182,0.00013227513227513228
|
| 629 |
+
aggregate,aggregate,BIGGEN,biggen_240829.csv,kendall,random,11,2,0.8909090909090909,1.3728555395222063e-05
|
| 630 |
+
aggregate,aggregate,BIGGEN,biggen_240829.csv,kendall,random,11,3,0.8181818181818182,0.00013227513227513228
|
| 631 |
+
aggregate,aggregate,BIGGEN,biggen_240829.csv,kendall,random,11,4,0.7090909090909091,0.0015912097162097162
|
| 632 |
+
aggregate,aggregate,BIGGEN Grounding,biggen_240829.csv,kendall,random,11,0,0.7454545454545454,0.000759529822029822
|
| 633 |
+
aggregate,aggregate,BIGGEN Grounding,biggen_240829.csv,kendall,random,11,1,0.7818181818181819,0.0003334435626102293
|
| 634 |
+
aggregate,aggregate,BIGGEN Grounding,biggen_240829.csv,kendall,random,11,2,0.8181818181818182,0.00013227513227513228
|
| 635 |
+
aggregate,aggregate,BIGGEN Grounding,biggen_240829.csv,kendall,random,11,3,0.8073734277593311,0.0005907573118657002
|
| 636 |
+
aggregate,aggregate,BIGGEN Grounding,biggen_240829.csv,kendall,random,11,4,0.7454545454545454,0.000759529822029822
|
| 637 |
+
aggregate,aggregate,BIGGEN Instruction Following,biggen_240829.csv,kendall,random,11,0,0.587180674734059,0.01246215829454031
|
| 638 |
+
aggregate,aggregate,BIGGEN Instruction Following,biggen_240829.csv,kendall,random,11,1,0.6482593132545567,0.006117582447622459
|
| 639 |
+
aggregate,aggregate,BIGGEN Instruction Following,biggen_240829.csv,kendall,random,11,2,0.8545454545454545,4.624619207952541e-05
|
| 640 |
+
aggregate,aggregate,BIGGEN Instruction Following,biggen_240829.csv,kendall,random,11,3,0.7706746355884524,0.0010393630991335228
|
| 641 |
+
aggregate,aggregate,BIGGEN Instruction Following,biggen_240829.csv,kendall,random,11,4,0.5371291452680612,0.02311942970946668
|
| 642 |
+
aggregate,aggregate,BIGGEN Planning,biggen_240829.csv,kendall,random,11,0,0.6238794669049377,0.007931923532795268
|
| 643 |
+
aggregate,aggregate,BIGGEN Planning,biggen_240829.csv,kendall,random,11,1,0.4909090909090909,0.04053235730319064
|
| 644 |
+
aggregate,aggregate,BIGGEN Planning,biggen_240829.csv,kendall,random,11,2,0.8440722199302099,0.0003281542287518694
|
| 645 |
+
aggregate,aggregate,BIGGEN Planning,biggen_240829.csv,kendall,random,11,3,0.7454545454545454,0.000759529822029822
|
| 646 |
+
aggregate,aggregate,BIGGEN Planning,biggen_240829.csv,kendall,random,11,4,0.36698792170878686,0.11834981273562825
|
| 647 |
+
aggregate,aggregate,BIGGEN Reasoning,biggen_240829.csv,kendall,random,11,0,0.8909090909090909,1.3728555395222063e-05
|
| 648 |
+
aggregate,aggregate,BIGGEN Reasoning,biggen_240829.csv,kendall,random,11,1,0.9272727272727274,3.2567740901074234e-06
|
| 649 |
+
aggregate,aggregate,BIGGEN Reasoning,biggen_240829.csv,kendall,random,11,2,1.0,5.010421677088344e-08
|
| 650 |
+
aggregate,aggregate,BIGGEN Reasoning,biggen_240829.csv,kendall,random,11,3,0.7090909090909091,0.0015912097162097162
|
| 651 |
+
aggregate,aggregate,BIGGEN Reasoning,biggen_240829.csv,kendall,random,11,4,0.6727272727272727,0.0031063111271444604
|
| 652 |
+
aggregate,aggregate,BIGGEN Refinement,biggen_240829.csv,kendall,random,11,0,0.8181818181818182,0.00013227513227513228
|
| 653 |
+
aggregate,aggregate,BIGGEN Refinement,biggen_240829.csv,kendall,random,11,1,0.8073734277593311,0.0005907573118657002
|
| 654 |
+
aggregate,aggregate,BIGGEN Refinement,biggen_240829.csv,kendall,random,11,2,0.8909090909090909,1.3728555395222063e-05
|
| 655 |
+
aggregate,aggregate,BIGGEN Refinement,biggen_240829.csv,kendall,random,11,3,0.7818181818181819,0.0003334435626102293
|
| 656 |
+
aggregate,aggregate,BIGGEN Refinement,biggen_240829.csv,kendall,random,11,4,0.6605782590758164,0.004936818556325077
|
| 657 |
+
aggregate,aggregate,BIGGEN Safety,biggen_240829.csv,kendall,random,11,0,-0.0909090909090909,0.7611503928170594
|
| 658 |
+
aggregate,aggregate,BIGGEN Safety,biggen_240829.csv,kendall,random,11,1,0.07339758434175737,0.7547764265871044
|
| 659 |
+
aggregate,aggregate,BIGGEN Safety,biggen_240829.csv,kendall,random,11,2,0.4403855060505442,0.06091869077971648
|
| 660 |
+
aggregate,aggregate,BIGGEN Safety,biggen_240829.csv,kendall,random,11,3,0.3302891295379082,0.15985367483762747
|
| 661 |
+
aggregate,aggregate,BIGGEN Safety,biggen_240829.csv,kendall,random,11,4,0.1272727272727273,0.6480954385121052
|
| 662 |
+
aggregate,aggregate,BIGGEN Theory of Mind,biggen_240829.csv,kendall,random,11,0,0.7090909090909091,0.0015912097162097162
|
| 663 |
+
aggregate,aggregate,BIGGEN Theory of Mind,biggen_240829.csv,kendall,random,11,1,0.7818181818181819,0.0003334435626102293
|
| 664 |
+
aggregate,aggregate,BIGGEN Theory of Mind,biggen_240829.csv,kendall,random,11,2,0.8705196492275474,0.00023202582506637044
|
| 665 |
+
aggregate,aggregate,BIGGEN Theory of Mind,biggen_240829.csv,kendall,random,11,3,0.7479575920067658,0.001637274718449882
|
| 666 |
+
aggregate,aggregate,BIGGEN Theory of Mind,biggen_240829.csv,kendall,random,11,4,0.5983660736054126,0.01175728488671479
|
| 667 |
+
aggregate,aggregate,BIGGEN Tool Usage,biggen_240829.csv,kendall,random,11,0,0.7090909090909091,0.0015912097162097162
|
| 668 |
+
aggregate,aggregate,BIGGEN Tool Usage,biggen_240829.csv,kendall,random,11,1,0.6000000000000001,0.00994553671637005
|
| 669 |
+
aggregate,aggregate,BIGGEN Tool Usage,biggen_240829.csv,kendall,random,11,2,0.7090909090909091,0.0015912097162097162
|
| 670 |
+
aggregate,aggregate,BIGGEN Tool Usage,biggen_240829.csv,kendall,random,11,3,0.7454545454545454,0.000759529822029822
|
| 671 |
+
aggregate,aggregate,BIGGEN Tool Usage,biggen_240829.csv,kendall,random,11,4,0.5272727272727272,0.02638447971781305
|
| 672 |
+
aggregate,aggregate,BIGGEN Multilingual,biggen_240829.csv,kendall,random,11,0,0.7706746355884524,0.0010393630991335228
|
| 673 |
+
aggregate,aggregate,BIGGEN Multilingual,biggen_240829.csv,kendall,random,11,1,0.8909090909090909,1.3728555395222063e-05
|
| 674 |
+
aggregate,aggregate,BIGGEN Multilingual,biggen_240829.csv,kendall,random,11,2,0.5272727272727272,0.02638447971781305
|
| 675 |
+
aggregate,aggregate,BIGGEN Multilingual,biggen_240829.csv,kendall,random,11,3,0.7454545454545454,0.000759529822029822
|
| 676 |
+
aggregate,aggregate,BIGGEN Multilingual,biggen_240829.csv,kendall,random,11,4,0.7818181818181819,0.0003334435626102293
|
| 677 |
+
aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,11,0,0.7818181818181819,0.0003334435626102293
|
| 678 |
+
aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,11,1,0.8545454545454545,4.624619207952541e-05
|
| 679 |
+
aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,11,2,0.7818181818181819,0.0003334435626102293
|
| 680 |
+
aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,11,3,0.8545454545454545,4.624619207952541e-05
|
| 681 |
+
aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,11,4,0.7818181818181819,0.0003334435626102293
|
| 682 |
+
aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,11,0,0.6731618328060892,0.004677734981047257
|
| 683 |
+
aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,11,1,0.759389481241052,0.0013210471654040124
|
| 684 |
+
aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,11,2,0.7339758434175737,0.0017872890369872653
|
| 685 |
+
aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,11,3,0.6238794669049377,0.007931923532795268
|
| 686 |
+
aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,11,4,0.7090909090909091,0.0015912097162097162
|
| 687 |
+
aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,11,0,0.6363636363636364,0.005707170915504249
|
| 688 |
+
aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,11,1,0.7454545454545454,0.000759529822029822
|
| 689 |
+
aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,11,2,0.7706746355884524,0.0010393630991335228
|
| 690 |
+
aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,11,3,0.8181818181818182,0.00013227513227513228
|
| 691 |
+
aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,11,4,0.7706746355884524,0.0010393630991335228
|
| 692 |
+
aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,11,0,0.7090909090909091,0.0015912097162097162
|
| 693 |
+
aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,11,1,0.8909090909090909,1.3728555395222063e-05
|
| 694 |
+
aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,11,2,0.7818181818181819,0.0003334435626102293
|
| 695 |
+
aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,11,3,0.8545454545454545,4.624619207952541e-05
|
| 696 |
+
aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,11,4,0.8545454545454545,4.624619207952541e-05
|
| 697 |
+
aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,11,0,0.5636363636363636,0.016540504248837583
|
| 698 |
+
aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,11,1,0.7454545454545454,0.000759529822029822
|
| 699 |
+
aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,11,2,0.6363636363636364,0.005707170915504249
|
| 700 |
+
aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,11,3,0.7818181818181819,0.0003334435626102293
|
| 701 |
+
aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,11,4,0.6363636363636364,0.005707170915504249
|
| 702 |
+
aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,11,0,0.7090909090909091,0.0015912097162097162
|
| 703 |
+
aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,11,1,0.8181818181818182,0.00013227513227513228
|
| 704 |
+
aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,11,2,0.5636363636363636,0.016540504248837583
|
| 705 |
+
aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,11,3,0.8545454545454545,4.624619207952541e-05
|
| 706 |
+
aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,11,4,0.7454545454545454,0.000759529822029822
|
| 707 |
+
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,11,0,0.6727272727272727,0.0031063111271444604
|
| 708 |
+
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,11,1,0.7454545454545454,0.000759529822029822
|
| 709 |
+
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,11,2,0.7090909090909091,0.0015912097162097162
|
| 710 |
+
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,11,3,0.6000000000000001,0.00994553671637005
|
| 711 |
+
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,11,4,0.7454545454545454,0.000759529822029822
|
cache/allbenchs_cache_741f08262e15cba4bd6c8b25f2b138ca.csv
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|