大模型 | 类别 | 总分 | 排名 | 分类能力 | 信息抽取 | 阅读理解 | 数据分析 | 指令遵从 | 算术运算 | 初中数学 | 符号推理 | 代词理解 | 诗词匹配 | 公务员考试 | 律师资格考试 | 高考 | 常识推理 | 文本蕴含 | 成语理解 | 情感分析 | 演绎推理 | C3中文阅读理解 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
DeepSeek-R1☛去体验 | 开源 | 90.6 | 1 | 94.1 | 95.7 | 92.2 | 100.0 | 81.1 | 96.6 | 94.2 | 93.2 | 94.6 | 89.8 | 88.6 | 71.7 | 93.5 | 79.8 | 77.1 | 94.0 | 94.1 | 92.7 | 98.9 |
DeepSeek-R1-Distill-Qwen-32B☛去体验 | 开源 | 85.7 | 2 | 86.3 | 95.7 | 84.4 | 96.0 | 78.8 | 94.7 | 90.2 | 88.1 | 94.4 | 88.6 | 76.2 | 49.2 | 84.0 | 75.8 | 70.2 | 85.8 | 97.4 | 95.9 | 95.8 |
qwen2.5-72b-instruct☛去体验 | 开源 | 85.2 | 3 | 92.0 | 87.4 | 91.7 | 92.7 | 83.0 | 95.5 | 91.1 | 85.8 | 91.3 | 86.6 | 71.7 | 49.1 | 82.5 | 75.8 | 62.7 | 89.0 | 96.0 | 95.1 | 100.0 |
deepseek-chat-v3☛去体验 | 开源 | 84.6 | 4 | 93.0 | 97.0 | 73.4 | 100.0 | 84.0 | 99.0 | 91.4 | 90.5 | 94.4 | 86.8 | 72.7 | 39.5 | 75.3 | 74.7 | 55.6 | 89.1 | 96.7 | 99.2 | 95.8 |
qwen2.5-32b-instruct☛去体验 | 开源 | 83.4 | 5 | 91.0 | 94.1 | 85.8 | 91.3 | 83.0 | 94.0 | 90.3 | 66.6 | 94.1 | 88.2 | 70.0 | 51.9 | 81.2 | 72.7 | 62.3 | 86.3 | 95.0 | 90.2 | 96.2 |
qwq-32b-preview☛去体验 | 开源 | 83.3 | 6 | 91.6 | 90.4 | 81.5 | 93.3 | 60.6 | 97.5 | 95.6 | 71.6 | 89.5 | 84.0 | 78.0 | 50.8 | 80.6 | 73.7 | 72.6 | 84.1 | 97.4 | 92.7 | 96.3 |
DeepSeek-R1-Distill-Llama-70B☛去体验 | 开源 | 82.6 | 7 | 88.4 | 94.8 | 78.9 | 96.0 | 73.3 | 90.0 | 87.6 | 86.4 | 95.1 | 86.0 | 77.5 | 35.2 | 74.1 | 77.8 | 67.5 | 75.6 | 94.5 | 95.1 | 96.2 |
Llama-3.3-70B-Instruct☛去体验 | 开源 | 80.8 | 8 | 97.0 | 94.8 | 77.1 | 99.3 | 80.9 | 93.5 | 75.8 | 90.1 | 87.5 | 79.4 | 66.4 | 29.4 | 61.3 | 70.7 | 60.3 | 83.1 | 96.7 | 95.1 | 96.9 |
Llama-3.3-70B-Instruct-fp8☛去体验 | 开源 | 80.2 | 9 | 93.0 | 96.3 | 76.3 | 100.0 | 83.5 | 94.2 | 70.5 | 89.9 | 87.1 | 77.2 | 64.8 | 28.5 | 60.3 | 69.7 | 62.3 | 82.1 | 96.9 | 95.1 | 96.7 |
Hermes-3-Llama-3.1-405B☛去体验 | 开源 | 80.2 | 10 | 94.0 | 92.6 | 78.1 | 100.0 | 80.1 | 90.2 | 80.1 | 90.7 | 86.1 | 83.0 | 64.7 | 29.4 | 62.4 | 64.6 | 63.9 | 84.8 | 96.2 | 87.8 | 95.0 |
Meta-Llama-3.1-405B-Instruct☛去体验 | 开源 | 79.7 | 11 | 90.0 | 90.4 | 76.5 | 98.7 | 76.7 | 95.0 | 64.2 | 91.0 | 88.9 | 79.7 | 64.2 | 37.4 | 60.4 | 75.8 | 57.9 | 87.6 | 97.2 | 85.4 | 97.6 |
qwen2.5-math-72b-instruct☛去体验 | 开源 | 78.7 | 12 | 90.5 | 88.8 | 72.0 | 100.0 | 59.7 | 97.7 | 96.4 | 59.0 | 87.5 | 76.0 | 68.0 | 31.0 | 71.7 | 70.7 | 60.7 | 77.4 | 95.7 | 98.4 | 95.0 |
Llama-3.1-Nemotron-70B-Instruct-fp8☛去体验 | 开源 | 78.7 | 13 | 97.0 | 97.8 | 76.7 | 100.0 | 75.8 | 93.5 | 64.1 | 84.6 | 89.2 | 81.6 | 63.7 | 33.1 | 55.8 | 75.8 | 62.3 | 82.3 | 96.0 | 69.9 | 96.3 |
Yi-1.5-34B-Chat☛去体验 | 开源 | 76.2 | 14 | 90.0 | 83.0 | 81.8 | 83.3 | 74.0 | 79.0 | 75.6 | 77.2 | 84.0 | 81.3 | 59.0 | 38.9 | 67.8 | 74.7 | 59.5 | 86.6 | 96.7 | 61.8 | 94.0 |
gemma-2-27b-it☛去体验 | 开源 | 74.3 | 15 | 92.0 | 93.3 | 74.8 | 96.7 | 83.1 | 88.3 | 66.4 | 74.8 | 80.5 | 80.0 | 57.1 | 22.9 | 53.2 | 71.7 | 61.9 | 82.3 | 96.4 | 42.3 | 94.1 |
WizardLM-2-8x22B☛去体验 | 开源 | 73.6 | 16 | 94.0 | 91.9 | 63.5 | 97.3 | 74.2 | 84.5 | 64.9 | 80.3 | 92.7 | 73.2 | 53.5 | 23.5 | 48.3 | 68.7 | 57.9 | 65.7 | 95.7 | 78.0 | 91.2 |
Mixtral-8x7B-Instruct-v0.1☛去体验 | 开源 | 61.8 | 17 | 92.0 | 86.7 | 60.9 | 90.0 | 64.4 | 69.8 | 46.8 | 63.0 | 81.2 | 73.0 | 47.8 | 18.1 | 42.6 | 62.6 | 46.8 | 56.5 | 87.4 | 0.0 | 84.9 |