| 类别 | 大模型 | 分类能力 | 排名 |
|---|---|---|---|
| 商用 | 360gpt2-pro | 99.0 | 1 |
| 商用 | 360gpt2-o1 | 98.0 | 2 |
| 开源 | Llama-3.1-Nemotron-70B-Instruct-fp8 | 97.0 | 3 |
| 商用 | Claude-3.5-Sonnet | 97.0 | 4 |
| 商用 | gemini-2.0-flash-exp | 97.0 | 5 |
| 商用 | 360gpt-turbo | 97.0 | 6 |
| 商用 | 360gpt-pro | 97.0 | 7 |
| 开源 | Llama-3.3-70B-Instruct | 97.0 | 8 |
| 开源 | phi-4 | 96.0 | 9 |
| 商用 | step-1-8k | 96.0 | 10 |
| 商用 | o3-mini | 95.3 | 11 |
| 商用 | gemini-2.0-flash-001 | 95.3 | 12 |
| 商用 | qwen2.5-max(new) | 95.0 | 13 |
| 商用 | gemini-2.0-pro-exp-02-05 | 94.1 | 14 |
| 开源 | DeepSeek-R1 | 94.1 | 15 |
| 开源 | WizardLM-2-8x22B | 94.0 | 16 |
| 商用 | ERNIE-3.5-8K | 94.0 | 17 |
| 商用 | yi-lightning | 94.0 | 18 |
| 商用 | SenseChat-5-1202(new) | 94.0 | 19 |
| 开源 | Hermes-3-Llama-3.1-405B | 94.0 | 20 |
| 商用 | o1-mini | 93.7 | 21 |
| 商用 | gemini-1.5-flash-8b | 93.0 | 22 |
| 开源 | Llama-3.3-70B-Instruct-fp8 | 93.0 | 23 |
| 商用 | hunyuan-turbo | 93.0 | 24 |
| 商用 | SenseChat-5 | 93.0 | 25 |
| 开源 | deepseek-chat-v3 | 93.0 | 26 |
| 商用 | gpt-4o | 93.0 | 27 |
| 商用 | ERNIE-Speed-Pro-128K(new) | 92.0 | 28 |
| 开源 | Mixtral-8x7B-Instruct-v0.1 | 92.0 | 29 |
| 开源 | gemma-2-27b-it | 92.0 | 30 |
| 商用 | MiniMax-Text-01(new) | 92.0 | 31 |
| 商用 | qwen-max | 92.0 | 32 |
| 商用 | moonshot-v1-8k | 92.0 | 33 |
| 开源 | qwen2.5-72b-instruct | 92.0 | 34 |
| 开源 | qwq-32b-preview | 91.6 | 35 |
| 开源 | qwen2.5-32b-instruct | 91.0 | 36 |
| 商用 | step-1-flash | 91.0 | 37 |
| 商用 | Baichuan4-Turbo | 91.0 | 38 |
| 商用 | gemini-1.5-flash | 91.0 | 39 |
| 商用 | mistral-small | 91.0 | 40 |
| 商用 | SenseChat-Turbo-1202(new) | 91.0 | 41 |
| 商用 | hunyuan-large | 91.0 | 42 |
| 开源 | qwen2.5-math-72b-instruct | 90.5 | 43 |
| 开源 | Meta-Llama-3.1-405B-Instruct | 90.0 | 44 |
| 商用 | gpt-4o-mini | 90.0 | 45 |
| 开源 | glm-4-9b-chat | 90.0 | 46 |
| 商用 | Baichuan4-Air | 90.0 | 47 |
| 开源 | Yi-1.5-34B-Chat | 90.0 | 48 |
| 商用 | ERNIE-4.0-Turbo-8K | 90.0 | 49 |
| 开源 | qwen2.5-14b-instruct | 89.0 | 50 |
| 商用 | GLM-4-AirX | 89.0 | 51 |
| 商用 | GLM-4-Flash | 89.0 | 52 |
| 开源 | Mistral-Nemo-Instruct-2407 | 89.0 | 53 |
| 商用 | abab7-chat-preview | 89.0 | 54 |
| 商用 | GLM-Zero-Preview(new) | 89.0 | 55 |
| 商用 | qwen-long | 89.0 | 56 |
| 商用 | GLM-4-Air | 89.0 | 57 |
| 商用 | SenseChat-v4 | 89.0 | 58 |
| 开源 | DeepSeek-R1-Distill-Qwen-14B | 88.4 | 59 |
| 开源 | DeepSeek-R1-Distill-Llama-8B | 88.4 | 60 |
| 开源 | DeepSeek-R1-Distill-Llama-70B | 88.4 | 61 |
| 商用 | ERNIE-Speed-8K | 88.0 | 62 |
| 商用 | ERNIE-4.0 | 88.0 | 63 |
| 商用 | GLM-4-FlashX(new) | 88.0 | 64 |
| 商用 | qwen-plus | 88.0 | 65 |
| 商用 | xunfei-4.0Ultra | 88.0 | 66 |
| 商用 | ministral-8b | 88.0 | 67 |
| 商用 | gemini-2.0-flash-thinking-exp-01-21(new) | 88.0 | 68 |
| 商用 | mistral-large | 88.0 | 69 |
| 商用 | abab6.5s-chat | 87.0 | 70 |
| 商用 | xunfei-spark-pro | 87.0 | 71 |
| 商用 | GLM-4-Plus | 87.0 | 72 |
| 商用 | ERNIE-Lite-8K(new) | 87.0 | 73 |
| 商用 | hunyuan-standard | 87.0 | 74 |
| 商用 | gemini-1.5-pro | 87.0 | 75 |
| 商用 | xunfei-spark-max | 87.0 | 76 |
| 开源 | DeepSeek-R1-Distill-Qwen-32B | 86.3 | 77 |
| 商用 | Baichuan4 | 86.0 | 78 |
| 开源 | internlm2_5-7b-chat | 86.0 | 79 |
| 开源 | internlm2_5-20b-chat | 86.0 | 80 |
| 商用 | Doubao-pro-32k | 86.0 | 81 |
| 开源 | qwen2.5-7b-instruct | 85.0 | 82 |
| 开源 | gemma-2-9b-it | 85.0 | 83 |
| 商用 | GLM-4-Long | 85.0 | 84 |
| 商用 | gemini-2.0-flash-lite-preview-02-05 | 84.7 | 85 |
| 商用 | ERNIE-Lite-Pro-128K(new) | 84.0 | 86 |
| 商用 | qwen-turbo | 83.0 | 87 |
| 商用 | ministral-3b | 83.0 | 88 |
| 开源 | Mistral-7B-Instruct-v0.3 | 82.0 | 89 |
| 开源 | Yi-1.5-9B-Chat | 82.0 | 90 |
| 开源 | qwen2.5-3b-instruct | 81.0 | 91 |
| 商用 | SenseChat-Turbo | 81.0 | 92 |
| 开源 | Meta-Llama-3.1-8B-Instruct-fp8 | 77.0 | 93 |
| 商用 | Doubao-lite-32k | 77.0 | 94 |
| 开源 | Llama-3.2-3B-Instruct | 74.0 | 95 |
| 开源 | DeepSeek-R1-Distill-Qwen-1.5B | 73.7 | 96 |
| 开源 | qwen2.5-1.5b-instruct | 70.0 | 97 |
| 开源 | DeepSeek-R1-Distill-Qwen-7B | 69.5 | 98 |
| 商用 | ERNIE-Tiny-8K(new) | 68.0 | 99 |
| 开源 | Llama-3.1-8B-Instruct | 63.0 | 100 |
| 开源 | Llama-3.2-1B-Instruct | 56.0 | 101 |
| 开源 | qwen2.5-0.5b-instruct | 52.0 | 102 |
| 商用 | o1-preview | / | 103 |
