Spaces:
Running
Running
Commit
·
c5ebc43
1
Parent(s):
ce9edf3
add
Browse files- Acrostic.json +10 -10
- Crossword.json +10 -10
- Cryptogram.json +8 -8
- Drop_Quote.json +10 -10
- Logic_Puzzle.json +13 -13
- Overall.json +130 -0
- Sudoku.json +10 -10
- index.html +1 -0
Acrostic.json
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
{
|
| 3 |
"Model": "Llama-3.1-8B-Instruct",
|
| 4 |
"CR": "43.0",
|
| 5 |
-
"S-Acc": "5.
|
| 6 |
"EM": "0.0",
|
| 7 |
"PM-0.5": "0.0",
|
| 8 |
"Tokens": "3712"
|
|
@@ -29,7 +29,7 @@
|
|
| 29 |
"S-Acc": "7.9",
|
| 30 |
"EM": "0.0",
|
| 31 |
"PM-0.5": "0.0",
|
| 32 |
-
"Tokens": "
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"Model": "Mistral-Small-Instruct-2409",
|
|
@@ -37,7 +37,7 @@
|
|
| 37 |
"S-Acc": "5.5",
|
| 38 |
"EM": "0.0",
|
| 39 |
"PM-0.5": "0.0",
|
| 40 |
-
"Tokens": "
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"Model": "Mistral-Large-Instruct-2411",
|
|
@@ -69,7 +69,7 @@
|
|
| 69 |
"S-Acc": "39.3",
|
| 70 |
"EM": "0.0",
|
| 71 |
"PM-0.5": "18.0",
|
| 72 |
-
"Tokens": "
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"Model": "QwQ-32B-Preview",
|
|
@@ -85,23 +85,23 @@
|
|
| 85 |
"S-Acc": "62.2",
|
| 86 |
"EM": "0.0",
|
| 87 |
"PM-0.5": "83.0",
|
| 88 |
-
"Tokens": "
|
| 89 |
},
|
| 90 |
{
|
| 91 |
-
"Model": "Gemini-2.0-
|
| 92 |
"CR": "98.0",
|
| 93 |
"S-Acc": "48.0",
|
| 94 |
"EM": "0.0",
|
| 95 |
"PM-0.5": "48.0",
|
| 96 |
-
"Tokens": "
|
| 97 |
},
|
| 98 |
{
|
| 99 |
-
"Model": "Gemini-2.0-thinking",
|
| 100 |
"CR": "92.0",
|
| 101 |
"S-Acc": "40.7",
|
| 102 |
"EM": "0.0",
|
| 103 |
"PM-0.5": "27.0",
|
| 104 |
-
"Tokens": "
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"Model": "OpenAI-gpt-4o",
|
|
@@ -117,7 +117,7 @@
|
|
| 117 |
"S-Acc": "34.7",
|
| 118 |
"EM": "0.0",
|
| 119 |
"PM-0.5": "12.0",
|
| 120 |
-
"Tokens": "
|
| 121 |
},
|
| 122 |
{
|
| 123 |
"Model": "OpenAI-o1-preview",
|
|
|
|
| 2 |
{
|
| 3 |
"Model": "Llama-3.1-8B-Instruct",
|
| 4 |
"CR": "43.0",
|
| 5 |
+
"S-Acc": "5.6",
|
| 6 |
"EM": "0.0",
|
| 7 |
"PM-0.5": "0.0",
|
| 8 |
"Tokens": "3712"
|
|
|
|
| 29 |
"S-Acc": "7.9",
|
| 30 |
"EM": "0.0",
|
| 31 |
"PM-0.5": "0.0",
|
| 32 |
+
"Tokens": "4600"
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"Model": "Mistral-Small-Instruct-2409",
|
|
|
|
| 37 |
"S-Acc": "5.5",
|
| 38 |
"EM": "0.0",
|
| 39 |
"PM-0.5": "0.0",
|
| 40 |
+
"Tokens": "4171"
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"Model": "Mistral-Large-Instruct-2411",
|
|
|
|
| 69 |
"S-Acc": "39.3",
|
| 70 |
"EM": "0.0",
|
| 71 |
"PM-0.5": "18.0",
|
| 72 |
+
"Tokens": "4111"
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"Model": "QwQ-32B-Preview",
|
|
|
|
| 85 |
"S-Acc": "62.2",
|
| 86 |
"EM": "0.0",
|
| 87 |
"PM-0.5": "83.0",
|
| 88 |
+
"Tokens": "10077"
|
| 89 |
},
|
| 90 |
{
|
| 91 |
+
"Model": "Gemini-2.0-flash",
|
| 92 |
"CR": "98.0",
|
| 93 |
"S-Acc": "48.0",
|
| 94 |
"EM": "0.0",
|
| 95 |
"PM-0.5": "48.0",
|
| 96 |
+
"Tokens": "4020"
|
| 97 |
},
|
| 98 |
{
|
| 99 |
+
"Model": "Gemini-2.0-flash-thinking",
|
| 100 |
"CR": "92.0",
|
| 101 |
"S-Acc": "40.7",
|
| 102 |
"EM": "0.0",
|
| 103 |
"PM-0.5": "27.0",
|
| 104 |
+
"Tokens": "4257"
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"Model": "OpenAI-gpt-4o",
|
|
|
|
| 117 |
"S-Acc": "34.7",
|
| 118 |
"EM": "0.0",
|
| 119 |
"PM-0.5": "12.0",
|
| 120 |
+
"Tokens": "10952"
|
| 121 |
},
|
| 122 |
{
|
| 123 |
"Model": "OpenAI-o1-preview",
|
Crossword.json
CHANGED
|
@@ -5,7 +5,7 @@
|
|
| 5 |
"S-Acc": "23.3",
|
| 6 |
"EM": "0.0",
|
| 7 |
"PM-0.5": "14.0",
|
| 8 |
-
"Tokens": "
|
| 9 |
},
|
| 10 |
{
|
| 11 |
"Model": "Llama-3.1-70B-Instruct",
|
|
@@ -13,7 +13,7 @@
|
|
| 13 |
"S-Acc": "46.8",
|
| 14 |
"EM": "0.0",
|
| 15 |
"PM-0.5": "62.0",
|
| 16 |
-
"Tokens": "
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"Model": "Llama-3.3-70B-Instruct",
|
|
@@ -21,7 +21,7 @@
|
|
| 21 |
"S-Acc": "47.6",
|
| 22 |
"EM": "0.0",
|
| 23 |
"PM-0.5": "65.3",
|
| 24 |
-
"Tokens": "
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"Model": "Mistral-7B-Instruct-v0.3",
|
|
@@ -37,7 +37,7 @@
|
|
| 37 |
"S-Acc": "48.3",
|
| 38 |
"EM": "0.0",
|
| 39 |
"PM-0.5": "54.0",
|
| 40 |
-
"Tokens": "
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"Model": "Mistral-Large-Instruct-2411",
|
|
@@ -69,7 +69,7 @@
|
|
| 69 |
"S-Acc": "44.1",
|
| 70 |
"EM": "0.0",
|
| 71 |
"PM-0.5": "36.7",
|
| 72 |
-
"Tokens": "
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"Model": "QwQ-32B-Preview",
|
|
@@ -77,7 +77,7 @@
|
|
| 77 |
"S-Acc": "30.2",
|
| 78 |
"EM": "0.0",
|
| 79 |
"PM-0.5": "18.0",
|
| 80 |
-
"Tokens": "
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"Model": "DeepSeek-R1",
|
|
@@ -85,10 +85,10 @@
|
|
| 85 |
"S-Acc": "75.3",
|
| 86 |
"EM": "16.7",
|
| 87 |
"PM-0.5": "94.0",
|
| 88 |
-
"Tokens": "
|
| 89 |
},
|
| 90 |
{
|
| 91 |
-
"Model": "Gemini-2.0-
|
| 92 |
"CR": "98.7",
|
| 93 |
"S-Acc": "61.6",
|
| 94 |
"EM": "0.0",
|
|
@@ -96,7 +96,7 @@
|
|
| 96 |
"Tokens": "2555"
|
| 97 |
},
|
| 98 |
{
|
| 99 |
-
"Model": "Gemini-2.0-thinking",
|
| 100 |
"CR": "94.7",
|
| 101 |
"S-Acc": "57.7",
|
| 102 |
"EM": "1.3",
|
|
@@ -106,7 +106,7 @@
|
|
| 106 |
{
|
| 107 |
"Model": "OpenAI-gpt-4o",
|
| 108 |
"CR": "100.0",
|
| 109 |
-
"S-Acc": "
|
| 110 |
"EM": "1.3",
|
| 111 |
"PM-0.5": "86.7",
|
| 112 |
"Tokens": "1726"
|
|
|
|
| 5 |
"S-Acc": "23.3",
|
| 6 |
"EM": "0.0",
|
| 7 |
"PM-0.5": "14.0",
|
| 8 |
+
"Tokens": "2888"
|
| 9 |
},
|
| 10 |
{
|
| 11 |
"Model": "Llama-3.1-70B-Instruct",
|
|
|
|
| 13 |
"S-Acc": "46.8",
|
| 14 |
"EM": "0.0",
|
| 15 |
"PM-0.5": "62.0",
|
| 16 |
+
"Tokens": "3072"
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"Model": "Llama-3.3-70B-Instruct",
|
|
|
|
| 21 |
"S-Acc": "47.6",
|
| 22 |
"EM": "0.0",
|
| 23 |
"PM-0.5": "65.3",
|
| 24 |
+
"Tokens": "2613"
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"Model": "Mistral-7B-Instruct-v0.3",
|
|
|
|
| 37 |
"S-Acc": "48.3",
|
| 38 |
"EM": "0.0",
|
| 39 |
"PM-0.5": "54.0",
|
| 40 |
+
"Tokens": "3135"
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"Model": "Mistral-Large-Instruct-2411",
|
|
|
|
| 69 |
"S-Acc": "44.1",
|
| 70 |
"EM": "0.0",
|
| 71 |
"PM-0.5": "36.7",
|
| 72 |
+
"Tokens": "2735"
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"Model": "QwQ-32B-Preview",
|
|
|
|
| 77 |
"S-Acc": "30.2",
|
| 78 |
"EM": "0.0",
|
| 79 |
"PM-0.5": "18.0",
|
| 80 |
+
"Tokens": "4817"
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"Model": "DeepSeek-R1",
|
|
|
|
| 85 |
"S-Acc": "75.3",
|
| 86 |
"EM": "16.7",
|
| 87 |
"PM-0.5": "94.0",
|
| 88 |
+
"Tokens": "9810"
|
| 89 |
},
|
| 90 |
{
|
| 91 |
+
"Model": "Gemini-2.0-flash",
|
| 92 |
"CR": "98.7",
|
| 93 |
"S-Acc": "61.6",
|
| 94 |
"EM": "0.0",
|
|
|
|
| 96 |
"Tokens": "2555"
|
| 97 |
},
|
| 98 |
{
|
| 99 |
+
"Model": "Gemini-2.0-flash-thinking",
|
| 100 |
"CR": "94.7",
|
| 101 |
"S-Acc": "57.7",
|
| 102 |
"EM": "1.3",
|
|
|
|
| 106 |
{
|
| 107 |
"Model": "OpenAI-gpt-4o",
|
| 108 |
"CR": "100.0",
|
| 109 |
+
"S-Acc": "66.0",
|
| 110 |
"EM": "1.3",
|
| 111 |
"PM-0.5": "86.7",
|
| 112 |
"Tokens": "1726"
|
Cryptogram.json
CHANGED
|
@@ -5,7 +5,7 @@
|
|
| 5 |
"S-Acc": "2.3",
|
| 6 |
"EM": "0.0",
|
| 7 |
"PM-0.5": "0.0",
|
| 8 |
-
"Tokens": "
|
| 9 |
},
|
| 10 |
{
|
| 11 |
"Model": "Llama-3.1-70B-Instruct",
|
|
@@ -13,7 +13,7 @@
|
|
| 13 |
"S-Acc": "6.9",
|
| 14 |
"EM": "0.0",
|
| 15 |
"PM-0.5": "1.0",
|
| 16 |
-
"Tokens": "
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"Model": "Llama-3.3-70B-Instruct",
|
|
@@ -29,7 +29,7 @@
|
|
| 29 |
"S-Acc": "4.3",
|
| 30 |
"EM": "0.0",
|
| 31 |
"PM-0.5": "0.0",
|
| 32 |
-
"Tokens": "
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"Model": "Mistral-Small-Instruct-2409",
|
|
@@ -69,7 +69,7 @@
|
|
| 69 |
"S-Acc": "11.8",
|
| 70 |
"EM": "0.0",
|
| 71 |
"PM-0.5": "0.0",
|
| 72 |
-
"Tokens": "
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"Model": "QwQ-32B-Preview",
|
|
@@ -77,7 +77,7 @@
|
|
| 77 |
"S-Acc": "3.6",
|
| 78 |
"EM": "0.0",
|
| 79 |
"PM-0.5": "0.0",
|
| 80 |
-
"Tokens": "
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"Model": "DeepSeek-R1",
|
|
@@ -88,7 +88,7 @@
|
|
| 88 |
"Tokens": "10344"
|
| 89 |
},
|
| 90 |
{
|
| 91 |
-
"Model": "Gemini-2.0-
|
| 92 |
"CR": "47.0",
|
| 93 |
"S-Acc": "8.5",
|
| 94 |
"EM": "0.0",
|
|
@@ -96,7 +96,7 @@
|
|
| 96 |
"Tokens": "1585"
|
| 97 |
},
|
| 98 |
{
|
| 99 |
-
"Model": "Gemini-2.0-thinking",
|
| 100 |
"CR": "68.0",
|
| 101 |
"S-Acc": "11.2",
|
| 102 |
"EM": "0.0",
|
|
@@ -109,7 +109,7 @@
|
|
| 109 |
"S-Acc": "20.7",
|
| 110 |
"EM": "0.0",
|
| 111 |
"PM-0.5": "5.0",
|
| 112 |
-
"Tokens": "
|
| 113 |
},
|
| 114 |
{
|
| 115 |
"Model": "OpenAI-o1-mini",
|
|
|
|
| 5 |
"S-Acc": "2.3",
|
| 6 |
"EM": "0.0",
|
| 7 |
"PM-0.5": "0.0",
|
| 8 |
+
"Tokens": "2068"
|
| 9 |
},
|
| 10 |
{
|
| 11 |
"Model": "Llama-3.1-70B-Instruct",
|
|
|
|
| 13 |
"S-Acc": "6.9",
|
| 14 |
"EM": "0.0",
|
| 15 |
"PM-0.5": "1.0",
|
| 16 |
+
"Tokens": "1298"
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"Model": "Llama-3.3-70B-Instruct",
|
|
|
|
| 29 |
"S-Acc": "4.3",
|
| 30 |
"EM": "0.0",
|
| 31 |
"PM-0.5": "0.0",
|
| 32 |
+
"Tokens": "1096"
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"Model": "Mistral-Small-Instruct-2409",
|
|
|
|
| 69 |
"S-Acc": "11.8",
|
| 70 |
"EM": "0.0",
|
| 71 |
"PM-0.5": "0.0",
|
| 72 |
+
"Tokens": "1727"
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"Model": "QwQ-32B-Preview",
|
|
|
|
| 77 |
"S-Acc": "3.6",
|
| 78 |
"EM": "0.0",
|
| 79 |
"PM-0.5": "0.0",
|
| 80 |
+
"Tokens": "6492"
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"Model": "DeepSeek-R1",
|
|
|
|
| 88 |
"Tokens": "10344"
|
| 89 |
},
|
| 90 |
{
|
| 91 |
+
"Model": "Gemini-2.0-flash",
|
| 92 |
"CR": "47.0",
|
| 93 |
"S-Acc": "8.5",
|
| 94 |
"EM": "0.0",
|
|
|
|
| 96 |
"Tokens": "1585"
|
| 97 |
},
|
| 98 |
{
|
| 99 |
+
"Model": "Gemini-2.0-flash-thinking",
|
| 100 |
"CR": "68.0",
|
| 101 |
"S-Acc": "11.2",
|
| 102 |
"EM": "0.0",
|
|
|
|
| 109 |
"S-Acc": "20.7",
|
| 110 |
"EM": "0.0",
|
| 111 |
"PM-0.5": "5.0",
|
| 112 |
+
"Tokens": "740"
|
| 113 |
},
|
| 114 |
{
|
| 115 |
"Model": "OpenAI-o1-mini",
|
Drop_Quote.json
CHANGED
|
@@ -5,7 +5,7 @@
|
|
| 5 |
"S-Acc": "11.2",
|
| 6 |
"EM": "0.0",
|
| 7 |
"PM-0.5": "1.0",
|
| 8 |
-
"Tokens": "
|
| 9 |
},
|
| 10 |
{
|
| 11 |
"Model": "Llama-3.1-70B-Instruct",
|
|
@@ -29,7 +29,7 @@
|
|
| 29 |
"S-Acc": "6.6",
|
| 30 |
"EM": "0.0",
|
| 31 |
"PM-0.5": "1.0",
|
| 32 |
-
"Tokens": "
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"Model": "Mistral-Small-Instruct-2409",
|
|
@@ -37,7 +37,7 @@
|
|
| 37 |
"S-Acc": "26.9",
|
| 38 |
"EM": "0.0",
|
| 39 |
"PM-0.5": "6.0",
|
| 40 |
-
"Tokens": "
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"Model": "Mistral-Large-Instruct-2411",
|
|
@@ -45,7 +45,7 @@
|
|
| 45 |
"S-Acc": "24.7",
|
| 46 |
"EM": "0.0",
|
| 47 |
"PM-0.5": "9.0",
|
| 48 |
-
"Tokens": "
|
| 49 |
},
|
| 50 |
{
|
| 51 |
"Model": "Qwen2.5-7B-Instruct",
|
|
@@ -53,7 +53,7 @@
|
|
| 53 |
"S-Acc": "21.9",
|
| 54 |
"EM": "0.0",
|
| 55 |
"PM-0.5": "4.0",
|
| 56 |
-
"Tokens": "
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"Model": "Qwen2.5-32B-Instruct",
|
|
@@ -69,7 +69,7 @@
|
|
| 69 |
"S-Acc": "30.9",
|
| 70 |
"EM": "0.0",
|
| 71 |
"PM-0.5": "13.0",
|
| 72 |
-
"Tokens": "
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"Model": "QwQ-32B-Preview",
|
|
@@ -88,20 +88,20 @@
|
|
| 88 |
"Tokens": "11422"
|
| 89 |
},
|
| 90 |
{
|
| 91 |
-
"Model": "Gemini-2.0-
|
| 92 |
"CR": "92.0",
|
| 93 |
-
"S-Acc": "34.
|
| 94 |
"EM": "0.0",
|
| 95 |
"PM-0.5": "17.0",
|
| 96 |
"Tokens": "2717"
|
| 97 |
},
|
| 98 |
{
|
| 99 |
-
"Model": "Gemini-2.0-thinking",
|
| 100 |
"CR": "96.0",
|
| 101 |
"S-Acc": "34.4",
|
| 102 |
"EM": "0.0",
|
| 103 |
"PM-0.5": "23.0",
|
| 104 |
-
"Tokens": "
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"Model": "OpenAI-gpt-4o",
|
|
|
|
| 5 |
"S-Acc": "11.2",
|
| 6 |
"EM": "0.0",
|
| 7 |
"PM-0.5": "1.0",
|
| 8 |
+
"Tokens": "2123"
|
| 9 |
},
|
| 10 |
{
|
| 11 |
"Model": "Llama-3.1-70B-Instruct",
|
|
|
|
| 29 |
"S-Acc": "6.6",
|
| 30 |
"EM": "0.0",
|
| 31 |
"PM-0.5": "1.0",
|
| 32 |
+
"Tokens": "2337"
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"Model": "Mistral-Small-Instruct-2409",
|
|
|
|
| 37 |
"S-Acc": "26.9",
|
| 38 |
"EM": "0.0",
|
| 39 |
"PM-0.5": "6.0",
|
| 40 |
+
"Tokens": "1615"
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"Model": "Mistral-Large-Instruct-2411",
|
|
|
|
| 45 |
"S-Acc": "24.7",
|
| 46 |
"EM": "0.0",
|
| 47 |
"PM-0.5": "9.0",
|
| 48 |
+
"Tokens": "1566"
|
| 49 |
},
|
| 50 |
{
|
| 51 |
"Model": "Qwen2.5-7B-Instruct",
|
|
|
|
| 53 |
"S-Acc": "21.9",
|
| 54 |
"EM": "0.0",
|
| 55 |
"PM-0.5": "4.0",
|
| 56 |
+
"Tokens": "1852"
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"Model": "Qwen2.5-32B-Instruct",
|
|
|
|
| 69 |
"S-Acc": "30.9",
|
| 70 |
"EM": "0.0",
|
| 71 |
"PM-0.5": "13.0",
|
| 72 |
+
"Tokens": "1757"
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"Model": "QwQ-32B-Preview",
|
|
|
|
| 88 |
"Tokens": "11422"
|
| 89 |
},
|
| 90 |
{
|
| 91 |
+
"Model": "Gemini-2.0-flash",
|
| 92 |
"CR": "92.0",
|
| 93 |
+
"S-Acc": "34.3",
|
| 94 |
"EM": "0.0",
|
| 95 |
"PM-0.5": "17.0",
|
| 96 |
"Tokens": "2717"
|
| 97 |
},
|
| 98 |
{
|
| 99 |
+
"Model": "Gemini-2.0-flash-thinking",
|
| 100 |
"CR": "96.0",
|
| 101 |
"S-Acc": "34.4",
|
| 102 |
"EM": "0.0",
|
| 103 |
"PM-0.5": "23.0",
|
| 104 |
+
"Tokens": "3386"
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"Model": "OpenAI-gpt-4o",
|
Logic_Puzzle.json
CHANGED
|
@@ -5,7 +5,7 @@
|
|
| 5 |
"S-Acc": "16.0",
|
| 6 |
"EM": "0.0",
|
| 7 |
"PM-0.5": "8.0",
|
| 8 |
-
"Tokens": "
|
| 9 |
},
|
| 10 |
{
|
| 11 |
"Model": "Llama-3.1-70B-Instruct",
|
|
@@ -13,7 +13,7 @@
|
|
| 13 |
"S-Acc": "22.8",
|
| 14 |
"EM": "2.0",
|
| 15 |
"PM-0.5": "18.0",
|
| 16 |
-
"Tokens": "
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"Model": "Llama-3.3-70B-Instruct",
|
|
@@ -29,7 +29,7 @@
|
|
| 29 |
"S-Acc": "19.1",
|
| 30 |
"EM": "0.0",
|
| 31 |
"PM-0.5": "4.5",
|
| 32 |
-
"Tokens": "
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"Model": "Mistral-Small-Instruct-2409",
|
|
@@ -45,7 +45,7 @@
|
|
| 45 |
"S-Acc": "38.3",
|
| 46 |
"EM": "3.0",
|
| 47 |
"PM-0.5": "30.5",
|
| 48 |
-
"Tokens": "
|
| 49 |
},
|
| 50 |
{
|
| 51 |
"Model": "Qwen2.5-7B-Instruct",
|
|
@@ -53,7 +53,7 @@
|
|
| 53 |
"S-Acc": "25.8",
|
| 54 |
"EM": "0.0",
|
| 55 |
"PM-0.5": "8.5",
|
| 56 |
-
"Tokens": "
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"Model": "Qwen2.5-32B-Instruct",
|
|
@@ -61,7 +61,7 @@
|
|
| 61 |
"S-Acc": "32.2",
|
| 62 |
"EM": "0.0",
|
| 63 |
"PM-0.5": "22.5",
|
| 64 |
-
"Tokens": "
|
| 65 |
},
|
| 66 |
{
|
| 67 |
"Model": "Qwen2.5-72B-Instruct",
|
|
@@ -69,7 +69,7 @@
|
|
| 69 |
"S-Acc": "34.0",
|
| 70 |
"EM": "0.0",
|
| 71 |
"PM-0.5": "23.0",
|
| 72 |
-
"Tokens": "
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"Model": "QwQ-32B-Preview",
|
|
@@ -77,7 +77,7 @@
|
|
| 77 |
"S-Acc": "46.3",
|
| 78 |
"EM": "19.5",
|
| 79 |
"PM-0.5": "48.0",
|
| 80 |
-
"Tokens": "
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"Model": "DeepSeek-R1",
|
|
@@ -85,23 +85,23 @@
|
|
| 85 |
"S-Acc": "69.4",
|
| 86 |
"EM": "42.5",
|
| 87 |
"PM-0.5": "68.0",
|
| 88 |
-
"Tokens": "
|
| 89 |
},
|
| 90 |
{
|
| 91 |
-
"Model": "Gemini-2.0-
|
| 92 |
"CR": "58.0",
|
| 93 |
"S-Acc": "24.2",
|
| 94 |
"EM": "2.0",
|
| 95 |
"PM-0.5": "20.0",
|
| 96 |
-
"Tokens": "
|
| 97 |
},
|
| 98 |
{
|
| 99 |
-
"Model": "Gemini-2.0-thinking",
|
| 100 |
"CR": "99.0",
|
| 101 |
"S-Acc": "45.9",
|
| 102 |
"EM": "8.0",
|
| 103 |
"PM-0.5": "37.5",
|
| 104 |
-
"Tokens": "
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"Model": "OpenAI-gpt-4o",
|
|
|
|
| 5 |
"S-Acc": "16.0",
|
| 6 |
"EM": "0.0",
|
| 7 |
"PM-0.5": "8.0",
|
| 8 |
+
"Tokens": "1293"
|
| 9 |
},
|
| 10 |
{
|
| 11 |
"Model": "Llama-3.1-70B-Instruct",
|
|
|
|
| 13 |
"S-Acc": "22.8",
|
| 14 |
"EM": "2.0",
|
| 15 |
"PM-0.5": "18.0",
|
| 16 |
+
"Tokens": "1165"
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"Model": "Llama-3.3-70B-Instruct",
|
|
|
|
| 29 |
"S-Acc": "19.1",
|
| 30 |
"EM": "0.0",
|
| 31 |
"PM-0.5": "4.5",
|
| 32 |
+
"Tokens": "1618"
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"Model": "Mistral-Small-Instruct-2409",
|
|
|
|
| 45 |
"S-Acc": "38.3",
|
| 46 |
"EM": "3.0",
|
| 47 |
"PM-0.5": "30.5",
|
| 48 |
+
"Tokens": "1637"
|
| 49 |
},
|
| 50 |
{
|
| 51 |
"Model": "Qwen2.5-7B-Instruct",
|
|
|
|
| 53 |
"S-Acc": "25.8",
|
| 54 |
"EM": "0.0",
|
| 55 |
"PM-0.5": "8.5",
|
| 56 |
+
"Tokens": "1396"
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"Model": "Qwen2.5-32B-Instruct",
|
|
|
|
| 61 |
"S-Acc": "32.2",
|
| 62 |
"EM": "0.0",
|
| 63 |
"PM-0.5": "22.5",
|
| 64 |
+
"Tokens": "1208"
|
| 65 |
},
|
| 66 |
{
|
| 67 |
"Model": "Qwen2.5-72B-Instruct",
|
|
|
|
| 69 |
"S-Acc": "34.0",
|
| 70 |
"EM": "0.0",
|
| 71 |
"PM-0.5": "23.0",
|
| 72 |
+
"Tokens": "1810"
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"Model": "QwQ-32B-Preview",
|
|
|
|
| 77 |
"S-Acc": "46.3",
|
| 78 |
"EM": "19.5",
|
| 79 |
"PM-0.5": "48.0",
|
| 80 |
+
"Tokens": "9524"
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"Model": "DeepSeek-R1",
|
|
|
|
| 85 |
"S-Acc": "69.4",
|
| 86 |
"EM": "42.5",
|
| 87 |
"PM-0.5": "68.0",
|
| 88 |
+
"Tokens": "9205"
|
| 89 |
},
|
| 90 |
{
|
| 91 |
+
"Model": "Gemini-2.0-flash",
|
| 92 |
"CR": "58.0",
|
| 93 |
"S-Acc": "24.2",
|
| 94 |
"EM": "2.0",
|
| 95 |
"PM-0.5": "20.0",
|
| 96 |
+
"Tokens": "2104"
|
| 97 |
},
|
| 98 |
{
|
| 99 |
+
"Model": "Gemini-2.0-flash-thinking",
|
| 100 |
"CR": "99.0",
|
| 101 |
"S-Acc": "45.9",
|
| 102 |
"EM": "8.0",
|
| 103 |
"PM-0.5": "37.5",
|
| 104 |
+
"Tokens": "4038"
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"Model": "OpenAI-gpt-4o",
|
Overall.json
ADDED
|
@@ -0,0 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"Model": "Llama-3.1-8B-Instruct",
|
| 4 |
+
"CR": "42.6",
|
| 5 |
+
"S-Acc": "9.9",
|
| 6 |
+
"EM": "0.0",
|
| 7 |
+
"PM-0.5": "3.8",
|
| 8 |
+
"Tokens": "2478"
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"Model": "Llama-3.1-70B-Instruct",
|
| 12 |
+
"CR": "71.8",
|
| 13 |
+
"S-Acc": "27.4",
|
| 14 |
+
"EM": "0.5",
|
| 15 |
+
"PM-0.5": "21.9",
|
| 16 |
+
"Tokens": "2090"
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"Model": "Llama-3.3-70B-Instruct",
|
| 20 |
+
"CR": "92.4",
|
| 21 |
+
"S-Acc": "33.1",
|
| 22 |
+
"EM": "1.3",
|
| 23 |
+
"PM-0.5": "25.8",
|
| 24 |
+
"Tokens": "1842"
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"Model": "Mistral-7B-Instruct-v0.3",
|
| 28 |
+
"CR": "85.8",
|
| 29 |
+
"S-Acc": "12.1",
|
| 30 |
+
"EM": "0.0",
|
| 31 |
+
"PM-0.5": "2.3",
|
| 32 |
+
"Tokens": "2736"
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"Model": "Mistral-Small-Instruct-2409",
|
| 36 |
+
"CR": "91.0",
|
| 37 |
+
"S-Acc": "23.1",
|
| 38 |
+
"EM": "0.2",
|
| 39 |
+
"PM-0.5": "13.3",
|
| 40 |
+
"Tokens": "2273"
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"Model": "Mistral-Large-Instruct-2411",
|
| 44 |
+
"CR": "96.1",
|
| 45 |
+
"S-Acc": "36.4",
|
| 46 |
+
"EM": "2.5",
|
| 47 |
+
"PM-0.5": "30.0",
|
| 48 |
+
"Tokens": "2313"
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"Model": "Qwen2.5-7B-Instruct",
|
| 52 |
+
"CR": "85.1",
|
| 53 |
+
"S-Acc": "17.7",
|
| 54 |
+
"EM": "0.3",
|
| 55 |
+
"PM-0.5": "5.1",
|
| 56 |
+
"Tokens": "2086"
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"Model": "Qwen2.5-32B-Instruct",
|
| 60 |
+
"CR": "96.2",
|
| 61 |
+
"S-Acc": "29.9",
|
| 62 |
+
"EM": "0.6",
|
| 63 |
+
"PM-0.5": "14.8",
|
| 64 |
+
"Tokens": "1924"
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"Model": "Qwen2.5-72B-Instruct",
|
| 68 |
+
"CR": "95.0",
|
| 69 |
+
"S-Acc": "33.9",
|
| 70 |
+
"EM": "0.9",
|
| 71 |
+
"PM-0.5": "20.8",
|
| 72 |
+
"Tokens": "2359"
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"Model": "QwQ-32B-Preview",
|
| 76 |
+
"CR": "65.0",
|
| 77 |
+
"S-Acc": "26.6",
|
| 78 |
+
"EM": "8.5",
|
| 79 |
+
"PM-0.5": "19.3",
|
| 80 |
+
"Tokens": "6709"
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"Model": "DeepSeek-R1",
|
| 84 |
+
"CR": "100.0",
|
| 85 |
+
"S-Acc": "58.4",
|
| 86 |
+
"EM": "20.0",
|
| 87 |
+
"PM-0.5": "62.0",
|
| 88 |
+
"Tokens": "9856"
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"Model": "Gemini-2.0-flash",
|
| 92 |
+
"CR": "81.1",
|
| 93 |
+
"S-Acc": "37.0",
|
| 94 |
+
"EM": "2.4",
|
| 95 |
+
"PM-0.5": "34.5",
|
| 96 |
+
"Tokens": "2637"
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"Model": "Gemini-2.0-flash-thinking",
|
| 100 |
+
"CR": "88.2",
|
| 101 |
+
"S-Acc": "39.4",
|
| 102 |
+
"EM": "4.3",
|
| 103 |
+
"PM-0.5": "35.0",
|
| 104 |
+
"Tokens": "3725"
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"Model": "OpenAI-gpt-4o",
|
| 108 |
+
"CR": "99.8",
|
| 109 |
+
"S-Acc": "43.7",
|
| 110 |
+
"EM": "3.2",
|
| 111 |
+
"PM-0.5": "41.7",
|
| 112 |
+
"Tokens": "1486"
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"Model": "OpenAI-o1-mini",
|
| 116 |
+
"CR": "97.7",
|
| 117 |
+
"S-Acc": "41.3",
|
| 118 |
+
"EM": "9.1",
|
| 119 |
+
"PM-0.5": "32.8",
|
| 120 |
+
"Tokens": "9576"
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"Model": "OpenAI-o1-preview",
|
| 124 |
+
"CR": "96.3",
|
| 125 |
+
"S-Acc": "58.7",
|
| 126 |
+
"EM": "23.6",
|
| 127 |
+
"PM-0.5": "61.7",
|
| 128 |
+
"Tokens": "11436"
|
| 129 |
+
}
|
| 130 |
+
]
|
Sudoku.json
CHANGED
|
@@ -13,7 +13,7 @@
|
|
| 13 |
"S-Acc": "24.2",
|
| 14 |
"EM": "1.0",
|
| 15 |
"PM-0.5": "17.5",
|
| 16 |
-
"Tokens": "
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"Model": "Llama-3.3-70B-Instruct",
|
|
@@ -21,7 +21,7 @@
|
|
| 21 |
"S-Acc": "34.8",
|
| 22 |
"EM": "7.0",
|
| 23 |
"PM-0.5": "22.5",
|
| 24 |
-
"Tokens": "
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"Model": "Mistral-7B-Instruct-v0.3",
|
|
@@ -61,7 +61,7 @@
|
|
| 61 |
"S-Acc": "42.8",
|
| 62 |
"EM": "3.5",
|
| 63 |
"PM-0.5": "30.5",
|
| 64 |
-
"Tokens": "
|
| 65 |
},
|
| 66 |
{
|
| 67 |
"Model": "Qwen2.5-72B-Instruct",
|
|
@@ -85,10 +85,10 @@
|
|
| 85 |
"S-Acc": "70.3",
|
| 86 |
"EM": "50.0",
|
| 87 |
"PM-0.5": "64.0",
|
| 88 |
-
"Tokens": "
|
| 89 |
},
|
| 90 |
{
|
| 91 |
-
"Model": "Gemini-2.0-
|
| 92 |
"CR": "93.0",
|
| 93 |
"S-Acc": "45.3",
|
| 94 |
"EM": "12.5",
|
|
@@ -96,12 +96,12 @@
|
|
| 96 |
"Tokens": "2842"
|
| 97 |
},
|
| 98 |
{
|
| 99 |
-
"Model": "Gemini-2.0-thinking",
|
| 100 |
"CR": "79.5",
|
| 101 |
"S-Acc": "46.5",
|
| 102 |
"EM": "16.5",
|
| 103 |
"PM-0.5": "41.0",
|
| 104 |
-
"Tokens": "
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"Model": "OpenAI-gpt-4o",
|
|
@@ -109,7 +109,7 @@
|
|
| 109 |
"S-Acc": "52.2",
|
| 110 |
"EM": "14.5",
|
| 111 |
"PM-0.5": "48.0",
|
| 112 |
-
"Tokens": "
|
| 113 |
},
|
| 114 |
{
|
| 115 |
"Model": "OpenAI-o1-mini",
|
|
@@ -117,7 +117,7 @@
|
|
| 117 |
"S-Acc": "53.4",
|
| 118 |
"EM": "27.0",
|
| 119 |
"PM-0.5": "43.0",
|
| 120 |
-
"Tokens": "
|
| 121 |
},
|
| 122 |
{
|
| 123 |
"Model": "OpenAI-o1-preview",
|
|
@@ -125,6 +125,6 @@
|
|
| 125 |
"S-Acc": "65.1",
|
| 126 |
"EM": "50.0",
|
| 127 |
"PM-0.5": "55.5",
|
| 128 |
-
"Tokens": "
|
| 129 |
}
|
| 130 |
]
|
|
|
|
| 13 |
"S-Acc": "24.2",
|
| 14 |
"EM": "1.0",
|
| 15 |
"PM-0.5": "17.5",
|
| 16 |
+
"Tokens": "1940"
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"Model": "Llama-3.3-70B-Instruct",
|
|
|
|
| 21 |
"S-Acc": "34.8",
|
| 22 |
"EM": "7.0",
|
| 23 |
"PM-0.5": "22.5",
|
| 24 |
+
"Tokens": "1062"
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"Model": "Mistral-7B-Instruct-v0.3",
|
|
|
|
| 61 |
"S-Acc": "42.8",
|
| 62 |
"EM": "3.5",
|
| 63 |
"PM-0.5": "30.5",
|
| 64 |
+
"Tokens": "1202"
|
| 65 |
},
|
| 66 |
{
|
| 67 |
"Model": "Qwen2.5-72B-Instruct",
|
|
|
|
| 85 |
"S-Acc": "70.3",
|
| 86 |
"EM": "50.0",
|
| 87 |
"PM-0.5": "64.0",
|
| 88 |
+
"Tokens": "8277"
|
| 89 |
},
|
| 90 |
{
|
| 91 |
+
"Model": "Gemini-2.0-flash",
|
| 92 |
"CR": "93.0",
|
| 93 |
"S-Acc": "45.3",
|
| 94 |
"EM": "12.5",
|
|
|
|
| 96 |
"Tokens": "2842"
|
| 97 |
},
|
| 98 |
{
|
| 99 |
+
"Model": "Gemini-2.0-flash-thinking",
|
| 100 |
"CR": "79.5",
|
| 101 |
"S-Acc": "46.5",
|
| 102 |
"EM": "16.5",
|
| 103 |
"PM-0.5": "41.0",
|
| 104 |
+
"Tokens": "3853"
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"Model": "OpenAI-gpt-4o",
|
|
|
|
| 109 |
"S-Acc": "52.2",
|
| 110 |
"EM": "14.5",
|
| 111 |
"PM-0.5": "48.0",
|
| 112 |
+
"Tokens": "1104"
|
| 113 |
},
|
| 114 |
{
|
| 115 |
"Model": "OpenAI-o1-mini",
|
|
|
|
| 117 |
"S-Acc": "53.4",
|
| 118 |
"EM": "27.0",
|
| 119 |
"PM-0.5": "43.0",
|
| 120 |
+
"Tokens": "3961"
|
| 121 |
},
|
| 122 |
{
|
| 123 |
"Model": "OpenAI-o1-preview",
|
|
|
|
| 125 |
"S-Acc": "65.1",
|
| 126 |
"EM": "50.0",
|
| 127 |
"PM-0.5": "55.5",
|
| 128 |
+
"Tokens": "8062"
|
| 129 |
}
|
| 130 |
]
|
index.html
CHANGED
|
@@ -203,6 +203,7 @@
|
|
| 203 |
document.getElementById("defaultOpen").click();
|
| 204 |
|
| 205 |
const urls = {
|
|
|
|
| 206 |
'Acrostic': 'Acrostic.json',
|
| 207 |
'Drop Quote': 'Drop_Quote.json',
|
| 208 |
'Crossword': 'Crossword.json',
|
|
|
|
| 203 |
document.getElementById("defaultOpen").click();
|
| 204 |
|
| 205 |
const urls = {
|
| 206 |
+
'Overall': 'Overall.json',
|
| 207 |
'Acrostic': 'Acrostic.json',
|
| 208 |
'Drop Quote': 'Drop_Quote.json',
|
| 209 |
'Crossword': 'Crossword.json',
|