Update space
Browse files
src/results/models_2024-10-07-14:50:12.666068.jsonl
ADDED
|
@@ -0,0 +1,677 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{"config": {
|
| 3 |
+
"model_name": "ChatGPT-4o-latest (2024-09-03)",
|
| 4 |
+
"organization": "OpenAI",
|
| 5 |
+
"license": "Proprietary",
|
| 6 |
+
"knowledge_cutoff": "2023/10"
|
| 7 |
+
},
|
| 8 |
+
"results": {
|
| 9 |
+
"math-algebra": {"Score": 99.19484702, "Avg Rank": 1.666666667, "Min Rank": 1, "Max Rank": 3},
|
| 10 |
+
"math-probability": {"Score": 100, "Avg Rank": 1, "Min Rank": 1, "Max Rank": 1},
|
| 11 |
+
"reasoning-logical": {"Avg Rank": 1, "Min Rank": 1, "Max Rank": 1},
|
| 12 |
+
"overall": {"Avg Rank": 2, "Min Rank": 2, "Max Rank": 2}
|
| 13 |
+
}},
|
| 14 |
+
|
| 15 |
+
{"config": {
|
| 16 |
+
"model_name": "gpt-4o-2024-08-06",
|
| 17 |
+
"organization": "OpenAI",
|
| 18 |
+
"license": "Proprietary",
|
| 19 |
+
"knowledge_cutoff": "2023/10"
|
| 20 |
+
},
|
| 21 |
+
"results": {
|
| 22 |
+
"math-algebra": {"Score": 98.38969404, "Avg Rank": 1.666666667, "Min Rank": 1, "Max Rank": 2},
|
| 23 |
+
"math-probability": {"Score": 96.49758454, "Avg Rank": 2.666666667, "Min Rank": 2, "Max Rank": 4},
|
| 24 |
+
"reasoning-logical": {"Avg Rank": 4.333333333, "Min Rank": 3, "Max Rank": 5},
|
| 25 |
+
"overall": {"Avg Rank": 7.33, "Min Rank": 4, "Max Rank": 9}
|
| 26 |
+
}},
|
| 27 |
+
|
| 28 |
+
{"config": {
|
| 29 |
+
"model_name": "gpt-4o-2024-05-13",
|
| 30 |
+
"organization": "OpenAI",
|
| 31 |
+
"license": "Proprietary",
|
| 32 |
+
"knowledge_cutoff": "2023/10"
|
| 33 |
+
},
|
| 34 |
+
"results": {
|
| 35 |
+
"math-algebra": {"Score": 98.15480333, "Avg Rank": 2.666666667, "Min Rank": 2, "Max Rank": 3},
|
| 36 |
+
"math-probability": {"Score": 94.83939431, "Avg Rank": 3.666666667, "Min Rank": 2, "Max Rank": 5},
|
| 37 |
+
"reasoning-logical": {"Avg Rank": 6.333333333, "Min Rank": 3, "Max Rank": 8},
|
| 38 |
+
"overall": {"Avg Rank": 7.67, "Min Rank": 7, "Max Rank": 9}
|
| 39 |
+
}},
|
| 40 |
+
|
| 41 |
+
{"config": {
|
| 42 |
+
"model_name": "gpt-4-turbo-2024-04-09",
|
| 43 |
+
"organization": "OpenAI",
|
| 44 |
+
"license": "Proprietary",
|
| 45 |
+
"knowledge_cutoff": "2023/12"
|
| 46 |
+
},
|
| 47 |
+
"results": {
|
| 48 |
+
"math-algebra": {"Score": 96.03195879, "Avg Rank": 4, "Min Rank": 4, "Max Rank": 4},
|
| 49 |
+
"math-probability": {"Score": 93.59903382, "Avg Rank": 6.666666667, "Min Rank": 6, "Max Rank": 8},
|
| 50 |
+
"reasoning-logical": {"Avg Rank": 4, "Min Rank": 2, "Max Rank": 7},
|
| 51 |
+
"overall": {"Avg Rank": 6, "Min Rank": 5, "Max Rank": 8}
|
| 52 |
+
}},
|
| 53 |
+
|
| 54 |
+
{"config": {
|
| 55 |
+
"model_name": "gemini-1.5-pro-001",
|
| 56 |
+
"organization": "Google",
|
| 57 |
+
"license": "Proprietary",
|
| 58 |
+
"knowledge_cutoff": "2024-01"
|
| 59 |
+
},
|
| 60 |
+
"results": {
|
| 61 |
+
"math-algebra": {"Score": 94.7572213, "Avg Rank": 5, "Min Rank": 5, "Max Rank": 5},
|
| 62 |
+
"math-probability": {"Score": 91.42512077, "Avg Rank": 9.666666667, "Min Rank": 9, "Max Rank": 10},
|
| 63 |
+
"reasoning-logical": {"Avg Rank": 9.666666667, "Min Rank": 9, "Max Rank": 11},
|
| 64 |
+
"overall": {"Avg Rank": 14, "Min Rank": 13, "Max Rank": 15}
|
| 65 |
+
}},
|
| 66 |
+
|
| 67 |
+
{"config": {
|
| 68 |
+
"model_name": "qwen2-72b-instruct",
|
| 69 |
+
"organization": "Alibaba",
|
| 70 |
+
"license": "Qianwen LICENSE",
|
| 71 |
+
"knowledge_cutoff": "2024-02"
|
| 72 |
+
},
|
| 73 |
+
"results": {
|
| 74 |
+
"math-algebra": {"Score": 93.88818605, "Avg Rank": 6, "Min Rank": 6, "Max Rank": 6},
|
| 75 |
+
"math-probability": {"Score": 91.54326174, "Avg Rank": 4, "Min Rank": 3, "Max Rank": 5},
|
| 76 |
+
"reasoning-logical": {"Avg Rank": 15.66666667, "Min Rank": 15, "Max Rank": 17},
|
| 77 |
+
"overall": {"Avg Rank": 17, "Min Rank": 17, "Max Rank": 17}
|
| 78 |
+
}},
|
| 79 |
+
|
| 80 |
+
{"config": {
|
| 81 |
+
"model_name": "gpt-4o-mini-2024-07-18",
|
| 82 |
+
"organization": "OpenAI",
|
| 83 |
+
"license": "Proprietary",
|
| 84 |
+
"knowledge_cutoff": "2024-07"
|
| 85 |
+
},
|
| 86 |
+
"results": {
|
| 87 |
+
"math-algebra": {"Score": 93.22073596, "Avg Rank": 7, "Min Rank": 7, "Max Rank": 7},
|
| 88 |
+
"math-probability": {"Score": 92.17351456, "Avg Rank": 3.666666667, "Min Rank": 3, "Max Rank": 5},
|
| 89 |
+
"reasoning-logical": {"Avg Rank": 9.666666667, "Min Rank": 9, "Max Rank": 10},
|
| 90 |
+
"overall": {"Avg Rank": 7, "Min Rank": 5, "Max Rank": 8}
|
| 91 |
+
}},
|
| 92 |
+
|
| 93 |
+
{"config": {
|
| 94 |
+
"model_name": "claude-3.5-sonnet",
|
| 95 |
+
"organization": "Anthropic",
|
| 96 |
+
"license": "Proprietary",
|
| 97 |
+
"knowledge_cutoff": "2024-03"
|
| 98 |
+
},
|
| 99 |
+
"results": {
|
| 100 |
+
"math-algebra": {"Score": 91.5823805, "Avg Rank": 8.333333333, "Min Rank": 8, "Max Rank": 9},
|
| 101 |
+
"math-probability": {"Score": 91.55011915, "Avg Rank": 8, "Min Rank": 7, "Max Rank": 9},
|
| 102 |
+
"reasoning-logical": {"Avg Rank": 5, "Min Rank": 2, "Max Rank": 7},
|
| 103 |
+
"overall": {"Avg Rank": 5, "Min Rank": 4, "Max Rank": 7}
|
| 104 |
+
}},
|
| 105 |
+
|
| 106 |
+
{"config": {
|
| 107 |
+
"model_name": "o1-mini",
|
| 108 |
+
"organization": "01 AI",
|
| 109 |
+
"license": "Proprietary",
|
| 110 |
+
"knowledge_cutoff": "2024-01"
|
| 111 |
+
},
|
| 112 |
+
"results": {
|
| 113 |
+
"math-algebra": None,
|
| 114 |
+
"math-probability": None,
|
| 115 |
+
"reasoning-logical": None,
|
| 116 |
+
"overall": {"Avg Rank": 1, "Min Rank": 1, "Max Rank": 1}
|
| 117 |
+
}},
|
| 118 |
+
|
| 119 |
+
{"config": {
|
| 120 |
+
"model_name": "o1-preview",
|
| 121 |
+
"organization": "01 AI",
|
| 122 |
+
"license": "Proprietary",
|
| 123 |
+
"knowledge_cutoff": "2024-01"
|
| 124 |
+
},
|
| 125 |
+
"results": {
|
| 126 |
+
"math-algebra": None,
|
| 127 |
+
"math-probability": None,
|
| 128 |
+
"reasoning-logical": None,
|
| 129 |
+
"overall": {"Avg Rank": 3, "Min Rank": 3, "Max Rank": 3}
|
| 130 |
+
}},
|
| 131 |
+
|
| 132 |
+
{"config": {
|
| 133 |
+
"model_name": "gemini-1.5-flash-001",
|
| 134 |
+
"organization": "Google",
|
| 135 |
+
"license": "Proprietary",
|
| 136 |
+
"knowledge_cutoff": "2024-02"
|
| 137 |
+
},
|
| 138 |
+
"results": {
|
| 139 |
+
"math-algebra": {"Score": 91.30211121, "Avg Rank": 11, "Min Rank": 11, "Max Rank": 11},
|
| 140 |
+
"math-probability": {"Score": 91.066099, "Avg Rank": 12, "Min Rank": 10, "Max Rank": 13},
|
| 141 |
+
"reasoning-logical": {"Avg Rank": 15.66666667, "Min Rank": 15, "Max Rank": 16},
|
| 142 |
+
"overall": {"Avg Rank": 14, "Min Rank": 13, "Max Rank": 15}
|
| 143 |
+
}},
|
| 144 |
+
|
| 145 |
+
{"config": {
|
| 146 |
+
"model_name": "gpt4-1106",
|
| 147 |
+
"organization": "OpenAI",
|
| 148 |
+
"license": "Proprietary",
|
| 149 |
+
"knowledge_cutoff": "2024-04"
|
| 150 |
+
},
|
| 151 |
+
"results": {
|
| 152 |
+
"math-algebra": {"Score": 91.2227739, "Avg Rank": 12, "Min Rank": 12, "Max Rank": 12},
|
| 153 |
+
"math-probability": {"Score": 91.09550085, "Avg Rank": 11.66666667, "Min Rank": 11, "Max Rank": 12},
|
| 154 |
+
"reasoning-logical": {"Avg Rank": 12, "Min Rank": 12, "Max Rank": 12},
|
| 155 |
+
"overall": {"Avg Rank": 12, "Min Rank": 11, "Max Rank": 12}
|
| 156 |
+
}},
|
| 157 |
+
|
| 158 |
+
{"config": {
|
| 159 |
+
"model_name": "gemma-2-27b-it",
|
| 160 |
+
"organization": "Google",
|
| 161 |
+
"license": "Gemma License",
|
| 162 |
+
"knowledge_cutoff": "2024-03"
|
| 163 |
+
},
|
| 164 |
+
"results": {
|
| 165 |
+
"math-algebra": {"Score": 91.08554346, "Avg Rank": 13.33333333, "Min Rank": 13, "Max Rank": 14},
|
| 166 |
+
"math-probability": {"Score": 91.09516215, "Avg Rank": 14, "Min Rank": 14, "Max Rank": 14},
|
| 167 |
+
"reasoning-logical": {"Avg Rank": 13, "Min Rank": 13, "Max Rank": 13},
|
| 168 |
+
"overall": {"Avg Rank": 13, "Min Rank": 12, "Max Rank": 14}
|
| 169 |
+
}},
|
| 170 |
+
|
| 171 |
+
{"config": {
|
| 172 |
+
"model_name": "claude-3-opus",
|
| 173 |
+
"organization": "Anthropic",
|
| 174 |
+
"license": "Proprietary",
|
| 175 |
+
"knowledge_cutoff": "2024-01"
|
| 176 |
+
},
|
| 177 |
+
"results": {
|
| 178 |
+
"math-algebra": {"Score": 89.75345785, "Avg Rank": 13.66666667, "Min Rank": 13, "Max Rank": 14},
|
| 179 |
+
"math-probability": {"Score": 91.06939607, "Avg Rank": 11.33333333, "Min Rank": 11, "Max Rank": 12},
|
| 180 |
+
"reasoning-logical": {"Avg Rank": 10.66666667, "Min Rank": 10, "Max Rank": 11},
|
| 181 |
+
"overall": {"Avg Rank": 12, "Min Rank": 10, "Max Rank": 15}
|
| 182 |
+
}},
|
| 183 |
+
|
| 184 |
+
{"config": {
|
| 185 |
+
"model_name": "gemma-2-9b-it-simpo",
|
| 186 |
+
"organization": "Google",
|
| 187 |
+
"license": "Gemma License",
|
| 188 |
+
"knowledge_cutoff": "2024-02"
|
| 189 |
+
},
|
| 190 |
+
"results": {
|
| 191 |
+
"math-algebra": {"Score": 87.66368227, "Avg Rank": 15, "Min Rank": 15, "Max Rank": 15},
|
| 192 |
+
"math-probability": {"Score": 73.64665336, "Avg Rank": 17, "Min Rank": 17, "Max Rank": 17},
|
| 193 |
+
"reasoning-logical": {"Avg Rank": 19, "Min Rank": 19, "Max Rank": 19},
|
| 194 |
+
"overall": {"Avg Rank": 17, "Min Rank": 15, "Max Rank": 19}
|
| 195 |
+
}},
|
| 196 |
+
|
| 197 |
+
{"config": {
|
| 198 |
+
"model_name": "qwen1.5-72b-chat",
|
| 199 |
+
"organization": "Alibaba",
|
| 200 |
+
"license": "Qianwen LICENSE",
|
| 201 |
+
"knowledge_cutoff": "2024-03"
|
| 202 |
+
},
|
| 203 |
+
"results": {
|
| 204 |
+
"math-algebra": {"Score": 86.56207015, "Avg Rank": 16, "Min Rank": 16, "Max Rank": 16},
|
| 205 |
+
"math-probability": {"Score": 72.7735874, "Avg Rank": 21, "Min Rank": 20, "Max Rank": 22},
|
| 206 |
+
"reasoning-logical": {"Avg Rank": 29.66666667, "Min Rank": 28, "Max Rank": 31},
|
| 207 |
+
"overall": {"Avg Rank": 23, "Min Rank": 16, "Max Rank": 31}
|
| 208 |
+
}},
|
| 209 |
+
|
| 210 |
+
{"config": {
|
| 211 |
+
"model_name": "qwen1.5-32b-chat",
|
| 212 |
+
"organization": "Alibaba",
|
| 213 |
+
"license": "Qianwen LICENSE",
|
| 214 |
+
"knowledge_cutoff": "2024-03"
|
| 215 |
+
},
|
| 216 |
+
"results": {
|
| 217 |
+
"math-algebra": {"Score": 84.59439036, "Avg Rank": 17.33333333, "Min Rank": 17, "Max Rank": 18},
|
| 218 |
+
"math-probability": {"Score": 76.61348265, "Avg Rank": 22.33333333, "Min Rank": 22, "Max Rank": 23},
|
| 219 |
+
"reasoning-logical": {"Avg Rank": 28.66666667, "Min Rank": 27, "Max Rank": 30},
|
| 220 |
+
"overall": {"Avg Rank": 22, "Min Rank": 17, "Max Rank": 30}
|
| 221 |
+
}},
|
| 222 |
+
|
| 223 |
+
{"config": {
|
| 224 |
+
"model_name": "google-gemma-2-9b-it",
|
| 225 |
+
"organization": "Google",
|
| 226 |
+
"license": "Proprietary",
|
| 227 |
+
"knowledge_cutoff": "2024-01"
|
| 228 |
+
},
|
| 229 |
+
"results": {
|
| 230 |
+
"math-algebra": {"Score": 84.18901776, "Avg Rank": 18, "Min Rank": 17, "Max Rank": 19},
|
| 231 |
+
"math-probability": {"Score": 74.46332504, "Avg Rank": 16, "Min Rank": 16, "Max Rank": 16},
|
| 232 |
+
"reasoning-logical": {"Avg Rank": 14, "Min Rank": 14, "Max Rank": 14},
|
| 233 |
+
"overall": {"Avg Rank": 16, "Min Rank": 14, "Max Rank": 19}
|
| 234 |
+
}},
|
| 235 |
+
|
| 236 |
+
{"config": {
|
| 237 |
+
"model_name": "yi-1.5-34b-chat",
|
| 238 |
+
"organization": "01 AI",
|
| 239 |
+
"license": "Proprietary",
|
| 240 |
+
"knowledge_cutoff": "2024-01"
|
| 241 |
+
},
|
| 242 |
+
"results": {
|
| 243 |
+
"math-algebra": {"Score": 81.82921677, "Avg Rank": 18.66666667, "Min Rank": 18, "Max Rank": 19},
|
| 244 |
+
"math-probability": {"Score": 77.41945842, "Avg Rank": 15, "Min Rank": 15, "Max Rank": 15},
|
| 245 |
+
"reasoning-logical": {"Avg Rank": 17.33333333, "Min Rank": 17, "Max Rank": 18},
|
| 246 |
+
"overall": {"Avg Rank": 18, "Min Rank": 15, "Max Rank": 19}
|
| 247 |
+
}},
|
| 248 |
+
|
| 249 |
+
{"config": {
|
| 250 |
+
"model_name": "meta-llama-3.1-8b-instruct",
|
| 251 |
+
"organization": "Meta",
|
| 252 |
+
"license": "Llama 3.1 Community",
|
| 253 |
+
"knowledge_cutoff": "2024-02"
|
| 254 |
+
},
|
| 255 |
+
"results": {
|
| 256 |
+
"math-algebra": {"Score": 75.57121963, "Avg Rank": 20.33333333, "Min Rank": 20, "Max Rank": 21},
|
| 257 |
+
"math-probability": {"Score": 75.46243493, "Avg Rank": 20.33333333, "Min Rank": 20, "Max Rank": 21},
|
| 258 |
+
"reasoning-logical": {"Avg Rank": 23.66666667, "Min Rank": 23, "Max Rank": 24},
|
| 259 |
+
"overall": {"Avg Rank": 21, "Min Rank": 20, "Max Rank": 24}
|
| 260 |
+
}},
|
| 261 |
+
|
| 262 |
+
{"config": {
|
| 263 |
+
"model_name": "gpt3.5-turbo-0125",
|
| 264 |
+
"organization": "OpenAI",
|
| 265 |
+
"license": "Proprietary",
|
| 266 |
+
"knowledge_cutoff": "2023-12"
|
| 267 |
+
},
|
| 268 |
+
"results": {
|
| 269 |
+
"math-algebra": {"Score": 73.29235048, "Avg Rank": 21.33333333, "Min Rank": 21, "Max Rank": 22},
|
| 270 |
+
"math-probability": {"Score": 66.27452275, "Avg Rank": 24, "Min Rank": 24, "Max Rank": 24},
|
| 271 |
+
"reasoning-logical": {"Avg Rank": 42.66666667, "Min Rank": 42, "Max Rank": 44},
|
| 272 |
+
"overall": {"Avg Rank": 29, "Min Rank": 21, "Max Rank": 44}
|
| 273 |
+
}},
|
| 274 |
+
|
| 275 |
+
{"config": {
|
| 276 |
+
"model_name": "llama-3-70b-instruct",
|
| 277 |
+
"organization": "Meta",
|
| 278 |
+
"license": "Llama 3 Community",
|
| 279 |
+
"knowledge_cutoff": "2024-03"
|
| 280 |
+
},
|
| 281 |
+
"results": {
|
| 282 |
+
"math-algebra": {"Score": 73.75419539, "Avg Rank": 21.33333333, "Min Rank": 20, "Max Rank": 22},
|
| 283 |
+
"math-probability": {"Score": 87.86358478, "Avg Rank": 18.33333333, "Min Rank": 18, "Max Rank": 19},
|
| 284 |
+
"reasoning-logical": {"Avg Rank": 3.333333333, "Min Rank": 2, "Max Rank": 4},
|
| 285 |
+
"overall": {"Avg Rank": 15, "Min Rank": 3, "Max Rank": 22}
|
| 286 |
+
}},
|
| 287 |
+
|
| 288 |
+
{"config": {
|
| 289 |
+
"model_name": "claude-3-sonnet",
|
| 290 |
+
"organization": "Anthropic",
|
| 291 |
+
"license": "Proprietary",
|
| 292 |
+
"knowledge_cutoff": "2024-02"
|
| 293 |
+
},
|
| 294 |
+
"results": {
|
| 295 |
+
"math-algebra": {"Score": 71.15353833, "Avg Rank": 23, "Min Rank": 23, "Max Rank": 23},
|
| 296 |
+
"math-probability": {"Score": 88.02362801, "Avg Rank": 18.66666667, "Min Rank": 18, "Max Rank": 19},
|
| 297 |
+
"reasoning-logical": {"Avg Rank": 17.33333333, "Min Rank": 16, "Max Rank": 18},
|
| 298 |
+
"overall": {"Avg Rank": 20, "Min Rank": 16, "Max Rank": 23}
|
| 299 |
+
}},
|
| 300 |
+
|
| 301 |
+
{"config": {
|
| 302 |
+
"model_name": "qwen1.5-14b-chat",
|
| 303 |
+
"organization": "Alibaba",
|
| 304 |
+
"license": "Qianwen LICENSE",
|
| 305 |
+
"knowledge_cutoff": "2024-01"
|
| 306 |
+
},
|
| 307 |
+
"results": {
|
| 308 |
+
"math-algebra": {"Score": 69.70470323, "Avg Rank": 24, "Min Rank": 24, "Max Rank": 24},
|
| 309 |
+
"math-probability": {"Score": 66.41420544, "Avg Rank": 28.66666667, "Min Rank": 28, "Max Rank": 29},
|
| 310 |
+
"reasoning-logical": {"Avg Rank": 34, "Min Rank": 34, "Max Rank": 34},
|
| 311 |
+
"overall": {"Avg Rank": 28, "Min Rank": 24, "Max Rank": 34}
|
| 312 |
+
}},
|
| 313 |
+
|
| 314 |
+
{"config": {
|
| 315 |
+
"model_name": "claude-3-haiku",
|
| 316 |
+
"organization": "Anthropic",
|
| 317 |
+
"license": "Proprietary",
|
| 318 |
+
"knowledge_cutoff": "2024-01"
|
| 319 |
+
},
|
| 320 |
+
"results": {
|
| 321 |
+
"math-algebra": {"Score": 68.44060149, "Avg Rank": 25, "Min Rank": 25, "Max Rank": 25},
|
| 322 |
+
"math-probability": {"Score": 76.46075239, "Avg Rank": 22.33333333, "Min Rank": 21, "Max Rank": 23},
|
| 323 |
+
"reasoning-logical": {"Avg Rank": 20, "Min Rank": 20, "Max Rank": 20},
|
| 324 |
+
"overall": {"Avg Rank": 22, "Min Rank": 20, "Max Rank": 25}
|
| 325 |
+
}},
|
| 326 |
+
|
| 327 |
+
{"config": {
|
| 328 |
+
"model_name": "claude-2.1",
|
| 329 |
+
"organization": "Anthropic",
|
| 330 |
+
"license": "Proprietary",
|
| 331 |
+
"knowledge_cutoff": "2023-12"
|
| 332 |
+
},
|
| 333 |
+
"results": {
|
| 334 |
+
"math-algebra": {"Score": 67.59939121, "Avg Rank": 26, "Min Rank": 26, "Max Rank": 26},
|
| 335 |
+
"math-probability": {"Score": 68.89772398, "Avg Rank": 27, "Min Rank": 27, "Max Rank": 27},
|
| 336 |
+
"reasoning-logical": {"Avg Rank": 21, "Min Rank": 21, "Max Rank": 21},
|
| 337 |
+
"overall": {"Avg Rank": 25, "Min Rank": 21, "Max Rank": 27}
|
| 338 |
+
}},
|
| 339 |
+
|
| 340 |
+
{"config": {
|
| 341 |
+
"model_name": "mistral-8x7b-instruct-v0.1",
|
| 342 |
+
"organization": "Mistral",
|
| 343 |
+
"license": "Apache 2.0",
|
| 344 |
+
"knowledge_cutoff": "2023-12"
|
| 345 |
+
},
|
| 346 |
+
"results": {
|
| 347 |
+
"math-algebra": {"Score": 64.71364004, "Avg Rank": 27, "Min Rank": 27, "Max Rank": 27},
|
| 348 |
+
"math-probability": {"Score": 67.67468595, "Avg Rank": 26, "Min Rank": 26, "Max Rank": 26},
|
| 349 |
+
"reasoning-logical": {"Avg Rank": 29, "Min Rank": 28, "Max Rank": 30},
|
| 350 |
+
"overall": {"Avg Rank": 27, "Min Rank": 26, "Max Rank": 30}
|
| 351 |
+
}},
|
| 352 |
+
|
| 353 |
+
{"config": {
|
| 354 |
+
"model_name": "claude-2.0",
|
| 355 |
+
"organization": "Anthropic",
|
| 356 |
+
"license": "Proprietary",
|
| 357 |
+
"knowledge_cutoff": "2023-10"
|
| 358 |
+
},
|
| 359 |
+
"results": {
|
| 360 |
+
"math-algebra": {"Score": 64.77311289, "Avg Rank": 28, "Min Rank": 28, "Max Rank": 28},
|
| 361 |
+
"math-probability": {"Score": 74.34063069, "Avg Rank": 25, "Min Rank": 25, "Max Rank": 25},
|
| 362 |
+
"reasoning-logical": {"Avg Rank": 23.33333333, "Min Rank": 23, "Max Rank": 24},
|
| 363 |
+
"overall": {"Avg Rank": 25, "Min Rank": 23, "Max Rank": 28}
|
| 364 |
+
}},
|
| 365 |
+
|
| 366 |
+
{"config": {
|
| 367 |
+
"model_name": "starling-lm-7b-beta",
|
| 368 |
+
"organization": "Nexusflow",
|
| 369 |
+
"license": "Apache-2.0",
|
| 370 |
+
"knowledge_cutoff": "2024-01"
|
| 371 |
+
},
|
| 372 |
+
"results": {
|
| 373 |
+
"math-algebra": {"Score": 64.01222884, "Avg Rank": 29.33333333, "Min Rank": 29, "Max Rank": 30},
|
| 374 |
+
"math-probability": {"Score": 70.42025806, "Avg Rank": 28.33333333, "Min Rank": 28, "Max Rank": 29},
|
| 375 |
+
"reasoning-logical": {"Avg Rank": 25, "Min Rank": 25, "Max Rank": 25},
|
| 376 |
+
"overall": {"Avg Rank": 27, "Min Rank": 25, "Max Rank": 30}
|
| 377 |
+
}},
|
| 378 |
+
|
| 379 |
+
{"config": {
|
| 380 |
+
"model_name": "gemini-1.0-pro-001",
|
| 381 |
+
"organization": "Google",
|
| 382 |
+
"license": "Proprietary",
|
| 383 |
+
"knowledge_cutoff": "2023-11"
|
| 384 |
+
},
|
| 385 |
+
"results": {
|
| 386 |
+
"math-algebra": {"Score": 63.93365247, "Avg Rank": 29.66666667, "Min Rank": 29, "Max Rank": 30},
|
| 387 |
+
"math-probability": {"Score": 62.13077748, "Avg Rank": 36.66666667, "Min Rank": 36, "Max Rank": 38},
|
| 388 |
+
"reasoning-logical": {"Avg Rank": 37.33333333, "Min Rank": 36, "Max Rank": 40},
|
| 389 |
+
"overall": {"Avg Rank": 34, "Min Rank": 29, "Max Rank": 40}
|
| 390 |
+
}},
|
| 391 |
+
|
| 392 |
+
{"config": {
|
| 393 |
+
"model_name": "openchat-3.5-0106",
|
| 394 |
+
"organization": "OpenChat",
|
| 395 |
+
"license": "Apache-2.0",
|
| 396 |
+
"knowledge_cutoff": "2024-01"
|
| 397 |
+
},
|
| 398 |
+
"results": {
|
| 399 |
+
"math-algebra": {"Score": 63.02959506, "Avg Rank": 31, "Min Rank": 31, "Max Rank": 31},
|
| 400 |
+
"math-probability": {"Score": 61.00599665, "Avg Rank": 30, "Min Rank": 30, "Max Rank": 30},
|
| 401 |
+
"reasoning-logical": {"Avg Rank": 27.66666667, "Min Rank": 27, "Max Rank": 29},
|
| 402 |
+
"overall": {"Avg Rank": 29, "Min Rank": 27, "Max Rank": 31}
|
| 403 |
+
}},
|
| 404 |
+
|
| 405 |
+
{"config": {
|
| 406 |
+
"model_name": "openchat-3.5",
|
| 407 |
+
"organization": "OpenChat",
|
| 408 |
+
"license": "Apache-2.0",
|
| 409 |
+
"knowledge_cutoff": "2023-12"
|
| 410 |
+
},
|
| 411 |
+
"results": {
|
| 412 |
+
"math-algebra": {"Score": 61.45954168, "Avg Rank": 32.33333333, "Min Rank": 32, "Max Rank": 33},
|
| 413 |
+
"math-probability": {"Score": 62.56195929, "Avg Rank": 32, "Min Rank": 32, "Max Rank": 32},
|
| 414 |
+
"reasoning-logical": {"Avg Rank": 32, "Min Rank": 31, "Max Rank": 33},
|
| 415 |
+
"overall": {"Avg Rank": 32, "Min Rank": 31, "Max Rank": 33}
|
| 416 |
+
}},
|
| 417 |
+
|
| 418 |
+
{"config": {
|
| 419 |
+
"model_name": "command-r-(08-2024)",
|
| 420 |
+
"organization": "Cohere",
|
| 421 |
+
"license": "CC-BY-NC-4.0",
|
| 422 |
+
"knowledge_cutoff": "2024-08"
|
| 423 |
+
},
|
| 424 |
+
"results": {
|
| 425 |
+
"math-algebra": {"Score": 61.0679475, "Avg Rank": 32.66666667, "Min Rank": 32, "Max Rank": 33},
|
| 426 |
+
"math-probability": {"Score": 66.00833826, "Avg Rank": 31, "Min Rank": 31, "Max Rank": 31},
|
| 427 |
+
"reasoning-logical": {"Avg Rank": 37.66666667, "Min Rank": 37, "Max Rank": 38},
|
| 428 |
+
"overall": {"Avg Rank": 34, "Min Rank": 31, "Max Rank": 38}
|
| 429 |
+
}},
|
| 430 |
+
|
| 431 |
+
{"config": {
|
| 432 |
+
"model_name": "gemma-1.1-7b-it",
|
| 433 |
+
"organization": "Google",
|
| 434 |
+
"license": "Gemma License",
|
| 435 |
+
"knowledge_cutoff": "2023-11"
|
| 436 |
+
},
|
| 437 |
+
"results": {
|
| 438 |
+
"math-algebra": {"Score": 60.92904194, "Avg Rank": 34.33333333, "Min Rank": 34, "Max Rank": 35},
|
| 439 |
+
"math-probability": {"Score": 62.17574935, "Avg Rank": 36.66666667, "Min Rank": 36, "Max Rank": 37},
|
| 440 |
+
"reasoning-logical": {"Avg Rank": 30.33333333, "Min Rank": 28, "Max Rank": 32},
|
| 441 |
+
"overall": {"Avg Rank": 34, "Min Rank": 28, "Max Rank": 37}
|
| 442 |
+
}},
|
| 443 |
+
|
| 444 |
+
{"config": {
|
| 445 |
+
"model_name": "llama3-8b-instruct",
|
| 446 |
+
"organization": "Meta",
|
| 447 |
+
"license": "Llama 3 Community",
|
| 448 |
+
"knowledge_cutoff": "2024-01"
|
| 449 |
+
},
|
| 450 |
+
"results": {
|
| 451 |
+
"math-algebra": {"Score": 61.06411319, "Avg Rank": 35, "Min Rank": 34, "Max Rank": 36},
|
| 452 |
+
"math-probability": {"Score": 62.13077748, "Avg Rank": 34.66666667, "Min Rank": 34, "Max Rank": 35},
|
| 453 |
+
"reasoning-logical": {"Avg Rank": 22, "Min Rank": 22, "Max Rank": 22},
|
| 454 |
+
"overall": {"Avg Rank": 30, "Min Rank": 22, "Max Rank": 36}
|
| 455 |
+
}},
|
| 456 |
+
|
| 457 |
+
{"config": {
|
| 458 |
+
"model_name": "gemma-2-2b-it",
|
| 459 |
+
"organization": "Google",
|
| 460 |
+
"license": "Gemma License",
|
| 461 |
+
"knowledge_cutoff": "2023-12"
|
| 462 |
+
},
|
| 463 |
+
"results": {
|
| 464 |
+
"math-algebra": {"Score": 59.70248014, "Avg Rank": 36, "Min Rank": 35, "Max Rank": 37},
|
| 465 |
+
"math-probability": {"Score": 61.08084527, "Avg Rank": 33.66666667, "Min Rank": 33, "Max Rank": 35},
|
| 466 |
+
"reasoning-logical": {"Avg Rank": 26, "Min Rank": 26, "Max Rank": 26},
|
| 467 |
+
"overall": {"Avg Rank": 32, "Min Rank": 26, "Max Rank": 37}
|
| 468 |
+
}},
|
| 469 |
+
|
| 470 |
+
{"config": {
|
| 471 |
+
"model_name": "starling-lm-7b-alpha",
|
| 472 |
+
"organization": "Nexusflow",
|
| 473 |
+
"license": "Apache-2.0",
|
| 474 |
+
"knowledge_cutoff": "2023-12"
|
| 475 |
+
},
|
| 476 |
+
"results": {
|
| 477 |
+
"math-algebra": {"Score": 59.574329, "Avg Rank": 36.66666667, "Min Rank": 36, "Max Rank": 37},
|
| 478 |
+
"math-probability": {"Score": 64.03683254, "Avg Rank": 33.66666667, "Min Rank": 33, "Max Rank": 34},
|
| 479 |
+
"reasoning-logical": {"Avg Rank": 35, "Min Rank": 35, "Max Rank": 35},
|
| 480 |
+
"overall": {"Avg Rank": 35, "Min Rank": 33, "Max Rank": 37}
|
| 481 |
+
}},
|
| 482 |
+
|
| 483 |
+
{"config": {
|
| 484 |
+
"model_name": "qwen1.5-4b-chat",
|
| 485 |
+
"organization": "Alibaba",
|
| 486 |
+
"license": "Qianwen LICENSE",
|
| 487 |
+
"knowledge_cutoff": "2024-02"
|
| 488 |
+
},
|
| 489 |
+
"results": {
|
| 490 |
+
"math-algebra": {"Score": 56.66282914, "Avg Rank": 38.33333333, "Min Rank": 38, "Max Rank": 39},
|
| 491 |
+
"math-probability": {"Score": 57.39032697, "Avg Rank": 43, "Min Rank": 43, "Max Rank": 43},
|
| 492 |
+
"reasoning-logical": {"Avg Rank": 46, "Min Rank": 46, "Max Rank": 46},
|
| 493 |
+
"overall": {"Avg Rank": 42, "Min Rank": 38, "Max Rank": 46}
|
| 494 |
+
}},
|
| 495 |
+
|
| 496 |
+
{"config": {
|
| 497 |
+
"model_name": "command-r-(04-2024)",
|
| 498 |
+
"organization": "Cohere",
|
| 499 |
+
"license": "CC-BY-NC-4.0",
|
| 500 |
+
"knowledge_cutoff": "2024-04"
|
| 501 |
+
},
|
| 502 |
+
"results": {
|
| 503 |
+
"math-algebra": {"Score": 56.19063413, "Avg Rank": 38.66666667, "Min Rank": 38, "Max Rank": 39},
|
| 504 |
+
"math-probability": {"Score": 54.37641509, "Avg Rank": 37.66666667, "Min Rank": 37, "Max Rank": 38},
|
| 505 |
+
"reasoning-logical": {"Avg Rank": 32.66666667, "Min Rank": 32, "Max Rank": 33},
|
| 506 |
+
"overall": {"Avg Rank": 36, "Min Rank": 32, "Max Rank": 39}
|
| 507 |
+
}},
|
| 508 |
+
|
| 509 |
+
{"config": {
|
| 510 |
+
"model_name": "vicuna-33b",
|
| 511 |
+
"organization": "LMSYS",
|
| 512 |
+
"license": "Non-commercial",
|
| 513 |
+
"knowledge_cutoff": "2023-12"
|
| 514 |
+
},
|
| 515 |
+
"results": {
|
| 516 |
+
"math-algebra": {"Score": 54.71037983, "Avg Rank": 40.66666667, "Min Rank": 40, "Max Rank": 42},
|
| 517 |
+
"math-probability": {"Score": 55.02214588, "Avg Rank": 41, "Min Rank": 41, "Max Rank": 41},
|
| 518 |
+
"reasoning-logical": {"Avg Rank": 41, "Min Rank": 41, "Max Rank": 41},
|
| 519 |
+
"overall": {"Avg Rank": 41, "Min Rank": 40, "Max Rank": 42}
|
| 520 |
+
}},
|
| 521 |
+
|
| 522 |
+
{"config": {
|
| 523 |
+
"model_name": "gemma-7b-it",
|
| 524 |
+
"organization": "Google",
|
| 525 |
+
"license": "Gemma License",
|
| 526 |
+
"knowledge_cutoff": "2023-12"
|
| 527 |
+
},
|
| 528 |
+
"results": {
|
| 529 |
+
"math-algebra": {"Score": 54.35817186, "Avg Rank": 40.66666667, "Min Rank": 40, "Max Rank": 41},
|
| 530 |
+
"math-probability": {"Score": 58.19573446, "Avg Rank": 42, "Min Rank": 42, "Max Rank": 42},
|
| 531 |
+
"reasoning-logical": {"Avg Rank": 39.33333333, "Min Rank": 39, "Max Rank": 40},
|
| 532 |
+
"overall": {"Avg Rank": 41, "Min Rank": 39, "Max Rank": 42}
|
| 533 |
+
}},
|
| 534 |
+
|
| 535 |
+
{"config": {
|
| 536 |
+
"model_name": "mistral-7b-instruct-2",
|
| 537 |
+
"organization": "Mistral",
|
| 538 |
+
"license": "Apache 2.0",
|
| 539 |
+
"knowledge_cutoff": "2023-12"
|
| 540 |
+
},
|
| 541 |
+
"results": {
|
| 542 |
+
"math-algebra": {"Score": 54.39240703, "Avg Rank": 41.66666667, "Min Rank": 41, "Max Rank": 42},
|
| 543 |
+
"math-probability": {"Score": 60.35257542, "Avg Rank": 39, "Min Rank": 39, "Max Rank": 39},
|
| 544 |
+
"reasoning-logical": {"Avg Rank": 36.66666667, "Min Rank": 36, "Max Rank": 37},
|
| 545 |
+
"overall": {"Avg Rank": 39, "Min Rank": 36, "Max Rank": 42}
|
| 546 |
+
}},
|
| 547 |
+
|
| 548 |
+
{"config": {
|
| 549 |
+
"model_name": "mistral-7b-instruct-1",
|
| 550 |
+
"organization": "Mistral",
|
| 551 |
+
"license": "Apache 2.0",
|
| 552 |
+
"knowledge_cutoff": "2023-12"
|
| 553 |
+
},
|
| 554 |
+
"results": {
|
| 555 |
+
"math-algebra": {"Score": 53.80157944, "Avg Rank": 43, "Min Rank": 43, "Max Rank": 43},
|
| 556 |
+
"math-probability": {"Score": 56.51960666, "Avg Rank": 40, "Min Rank": 40, "Max Rank": 40},
|
| 557 |
+
"reasoning-logical": {"Avg Rank": 45, "Min Rank": 45, "Max Rank": 45},
|
| 558 |
+
"overall": {"Avg Rank": 43, "Min Rank": 40, "Max Rank": 45}
|
| 559 |
+
}},
|
| 560 |
+
|
| 561 |
+
{"config": {
|
| 562 |
+
"model_name": "vicuna-13b",
|
| 563 |
+
"organization": "LMSYS",
|
| 564 |
+
"license": "Non-commercial",
|
| 565 |
+
"knowledge_cutoff": "2023-11"
|
| 566 |
+
},
|
| 567 |
+
"results": {
|
| 568 |
+
"math-algebra": {"Score": 53.5413765, "Avg Rank": 44, "Min Rank": 44, "Max Rank": 44},
|
| 569 |
+
"math-probability": {"Score": 53.53586693, "Avg Rank": 44, "Min Rank": 44, "Max Rank": 44},
|
| 570 |
+
"reasoning-logical": {"Avg Rank": 43.66666667, "Min Rank": 43, "Max Rank": 44},
|
| 571 |
+
"overall": {"Avg Rank": 44, "Min Rank": 43, "Max Rank": 44}
|
| 572 |
+
}},
|
| 573 |
+
|
| 574 |
+
{"config": {
|
| 575 |
+
"model_name": "zephyr-7b-beta",
|
| 576 |
+
"organization": "HuggingFace",
|
| 577 |
+
"license": "MIT",
|
| 578 |
+
"knowledge_cutoff": "2023-10"
|
| 579 |
+
},
|
| 580 |
+
"results": {
|
| 581 |
+
"math-algebra": {"Score": 52.23039742, "Avg Rank": 46, "Min Rank": 45, "Max Rank": 48},
|
| 582 |
+
"math-probability": {"Score": 51.67173535, "Avg Rank": 47.33333333, "Min Rank": 47, "Max Rank": 48},
|
| 583 |
+
"reasoning-logical": {"Avg Rank": 50, "Min Rank": 50, "Max Rank": 50},
|
| 584 |
+
"overall": {"Avg Rank": 48, "Min Rank": 45, "Max Rank": 50}
|
| 585 |
+
}},
|
| 586 |
+
|
| 587 |
+
{"config": {
|
| 588 |
+
"model_name": "gemma-1.1-2b-it",
|
| 589 |
+
"organization": "Google",
|
| 590 |
+
"license": "Gemma License",
|
| 591 |
+
"knowledge_cutoff": "2023-12"
|
| 592 |
+
},
|
| 593 |
+
"results": {
|
| 594 |
+
"math-algebra": {"Score": 52.22372428, "Avg Rank": 46, "Min Rank": 45, "Max Rank": 47},
|
| 595 |
+
"math-probability": {"Score": 51.74306688, "Avg Rank": 46.33333333, "Min Rank": 46, "Max Rank": 47},
|
| 596 |
+
"reasoning-logical": {"Avg Rank": 48, "Min Rank": 48, "Max Rank": 48},
|
| 597 |
+
"overall": {"Avg Rank": 47, "Min Rank": 45, "Max Rank": 48}
|
| 598 |
+
}},
|
| 599 |
+
|
| 600 |
+
{"config": {
|
| 601 |
+
"model_name": "llama2-7b-chat",
|
| 602 |
+
"organization": "Meta",
|
| 603 |
+
"license": "Llama 2 Community",
|
| 604 |
+
"knowledge_cutoff": "2023-10"
|
| 605 |
+
},
|
| 606 |
+
"results": {
|
| 607 |
+
"math-algebra": {"Score": 51.83025857, "Avg Rank": 46.33333333, "Min Rank": 46, "Max Rank": 47},
|
| 608 |
+
"math-probability": {"Score": 51.19585847, "Avg Rank": 47.33333333, "Min Rank": 46, "Max Rank": 48},
|
| 609 |
+
"reasoning-logical": {"Avg Rank": 42.66666667, "Min Rank": 42, "Max Rank": 43},
|
| 610 |
+
"overall": {"Avg Rank": 45, "Min Rank": 42, "Max Rank": 48}
|
| 611 |
+
}},
|
| 612 |
+
|
| 613 |
+
{"config": {
|
| 614 |
+
"model_name": "gemma-2b-it",
|
| 615 |
+
"organization": "Google",
|
| 616 |
+
"license": "Gemma License",
|
| 617 |
+
"knowledge_cutoff": "2023-11"
|
| 618 |
+
},
|
| 619 |
+
"results": {
|
| 620 |
+
"math-algebra": {"Score": 51.60281474, "Avg Rank": 47.66666667, "Min Rank": 47, "Max Rank": 48},
|
| 621 |
+
"math-probability": {"Score": 51.52250905, "Avg Rank": 50, "Min Rank": 50, "Max Rank": 50},
|
| 622 |
+
"reasoning-logical": {"Avg Rank": 51, "Min Rank": 51, "Max Rank": 51},
|
| 623 |
+
"overall": {"Avg Rank": 49, "Min Rank": 47, "Max Rank": 51}
|
| 624 |
+
}},
|
| 625 |
+
|
| 626 |
+
{"config": {
|
| 627 |
+
"model_name": "llama2-13b-chat",
|
| 628 |
+
"organization": "Meta",
|
| 629 |
+
"license": "Llama 2 Community",
|
| 630 |
+
"knowledge_cutoff": "2023-12"
|
| 631 |
+
},
|
| 632 |
+
"results": {
|
| 633 |
+
"math-algebra": {"Score": 51.21273132, "Avg Rank": 49, "Min Rank": 49, "Max Rank": 49},
|
| 634 |
+
"math-probability": {"Score": 51.72056522, "Avg Rank": 45, "Min Rank": 45, "Max Rank": 45},
|
| 635 |
+
"reasoning-logical": {"Avg Rank": 39, "Min Rank": 38, "Max Rank": 40},
|
| 636 |
+
"overall": {"Avg Rank": 44, "Min Rank": 38, "Max Rank": 49}
|
| 637 |
+
}},
|
| 638 |
+
|
| 639 |
+
{"config": {
|
| 640 |
+
"model_name": "vicuna-7b",
|
| 641 |
+
"organization": "LMSYS",
|
| 642 |
+
"license": "Non-commercial",
|
| 643 |
+
"knowledge_cutoff": "2023-11"
|
| 644 |
+
},
|
| 645 |
+
"results": {
|
| 646 |
+
"math-algebra": {"Score": 51.31450547, "Avg Rank": 50, "Min Rank": 50, "Max Rank": 50},
|
| 647 |
+
"math-probability": {"Score": 52.72504618, "Avg Rank": 49, "Min Rank": 49, "Max Rank": 49},
|
| 648 |
+
"reasoning-logical": {"Avg Rank": 47, "Min Rank": 47, "Max Rank": 47},
|
| 649 |
+
"overall": {"Avg Rank": 48, "Min Rank": 47, "Max Rank": 50}
|
| 650 |
+
}},
|
| 651 |
+
|
| 652 |
+
{"config": {
|
| 653 |
+
"model_name": "koala-13b",
|
| 654 |
+
"organization": "UC Berkeley",
|
| 655 |
+
"license": "Non-commercial",
|
| 656 |
+
"knowledge_cutoff": "2023-10"
|
| 657 |
+
},
|
| 658 |
+
"results": {
|
| 659 |
+
"math-algebra": {"Score": 50.19054677, "Avg Rank": 51, "Min Rank": 51, "Max Rank": 51},
|
| 660 |
+
"math-probability": {"Score": 50.741989, "Avg Rank": 51, "Min Rank": 51, "Max Rank": 51},
|
| 661 |
+
"reasoning-logical": {"Avg Rank": 49, "Min Rank": 49, "Max Rank": 49},
|
| 662 |
+
"overall": {"Avg Rank": 50, "Min Rank": 49, "Max Rank": 51}
|
| 663 |
+
}},
|
| 664 |
+
|
| 665 |
+
{"config": {
|
| 666 |
+
"model_name": "openassistant-pythia-12b",
|
| 667 |
+
"organization": "OpenAssistant",
|
| 668 |
+
"license": "Non-commercial",
|
| 669 |
+
"knowledge_cutoff": "2023-09"
|
| 670 |
+
},
|
| 671 |
+
"results": {
|
| 672 |
+
"math-algebra": {"Score": 50, "Avg Rank": 52, "Min Rank": 52, "Max Rank": 52},
|
| 673 |
+
"math-probability": {"Score": 50, "Avg Rank": 52, "Min Rank": 52, "Max Rank": 52},
|
| 674 |
+
"reasoning-logical": {"Avg Rank": 52, "Min Rank": 52, "Max Rank": 52},
|
| 675 |
+
"overall": {"Avg Rank": 52, "Min Rank": 52, "Max Rank": 52}
|
| 676 |
+
}}
|
| 677 |
+
]
|