大模型评测基准与性能对比

本页面展示了多个主流大模型在各项评测基准上的表现,包括MMLU、GSM8K、HumanEval等多个标准数据集。我们通过实时更新的评测结果,帮助开发者和研究人员了解不同大模型在各种任务下的表现。用户可以选择自定义模型与评测基准进行对比,快速获取不同模型在实际应用中的优劣势。

各个评测基准的详细介绍可见: LLM 评测基准列表与介绍

自定义评测选择

+
+
模型名称
MMLU Pro
知识问答
MMLU
知识问答
GSM8K
数学推理
MATH
数学推理
GPQA Diamond
常识推理
HumanEval
代码生成
MATH-500
数学推理
LiveCodeBench
代码生成
参数数量 开源情况 发布机构
OpenAI o1 91.04 91.80 0.00 96.40 77.30 0.00 96.40 71.00 未知 OpenAI
GPT-4.5 86.10 0.00 0.00 0.00 71.40 0.00 90.70 46.40 未知 OpenAI
OpenAI o3 85.60 0.00 0.00 0.00 83.30 0.00 0.00 0.00 未知 OpenAI
DeepSeek-R1 84.00 90.80 0.00 0.00 71.50 0.00 97.30 65.90 6710.0 DeepSeek-AI
Llama 4 Behemoth Instruct 82.20 0.00 0.00 0.00 73.70 0.00 95.00 49.40 20000.0 Facebook AI研究实验室
DeepSeek-V3-0324 81.20 0.00 0.00 0.00 68.40 0.00 94.00 49.20 6810.0 DeepSeek-AI
OpenAI o4 - mini 80.60 0.00 0.00 0.00 81.40 0.00 0.00 0.00 未知 OpenAI
Llama 4 Maverick Instruct 80.50 0.00 0.00 0.00 69.80 0.00 0.00 43.40 4000.0 Facebook AI研究实验室
GPT-4.1 80.50 0.00 0.00 0.00 66.30 0.00 0.00 0.00 未知 OpenAI
OpenAI o1-mini 80.30 85.20 0.00 0.00 60.00 92.40 90.00 52.00 未知 OpenAI
Gemini 2.0 Pro Experimental 79.10 86.50 0.00 91.80 64.70 0.00 0.00 0.00 未知 DeepMind
Hunyuan-TurboS 79.00 89.50 0.00 89.70 57.50 91.00 0.00 32.00 未知 腾讯AI实验室
GPT-4o 77.90 88.70 0.00 75.90 53.60 90.00 75.90 35.10 未知 OpenAI
GPT-4o(2024-11-20) 77.90 85.70 0.00 68.50 0.00 90.20 0.00 0.00 未知 OpenAI
Claude 3.5 Sonnet 77.64 88.30 0.00 71.10 59.40 92.00 0.00 0.00 未知 Anthropic
Gemini 2.0 Flash Experimental 76.24 0.00 0.00 0.00 0.00 0.00 0.00 0.00 未知 DeepMind
Qwen2.5-Max 76.10 87.90 94.50 68.50 0.00 73.20 0.00 0.00 未知 阿里巴巴
DeepSeek-V3 75.90 88.50 0.00 87.80 59.10 89.00 87.80 34.60 6810.0 DeepSeek-AI
Grok 2 75.50 87.50 0.00 76.10 56.00 88.40 0.00 0.00 未知 xAI
Llama 4 Scout Instruct 74.30 0.00 0.00 0.00 57.20 0.00 0.00 32.80 1090.0 Facebook AI研究实验室
Llama3.1-405B Instruct 73.40 88.60 0.00 73.90 49.00 89.00 0.00 30.20 4050.0 Facebook AI研究实验室
Qwen3-235B-A22B 68.18 0.00 94.39 0.00 0.00 0.00 0.00 70.70 2350.0 阿里巴巴
Llama 4 Maverick 62.90 85.50 0.00 61.20 0.00 0.00 0.00 0.00 4000.0 Facebook AI研究实验室
Llama3.1-405B 61.60 0.00 0.00 0.00 0.00 0.00 0.00 0.00 4050.0 Facebook AI研究实验室
Llama 4 Scout 58.20 79.60 0.00 50.30 0.00 0.00 0.00 0.00 1090.0 Facebook AI研究实验室
Mixtral-8x22B-Instruct-v0.1 56.33 0.00 0.00 0.00 0.00 0.00 0.00 0.00 1410.0 MistralAI
Grok-1.5 51.00 81.30 0.00 50.60 35.90 74.10 0.00 0.00 未知 xAI
Kimi k1.5 (Long-CoT) 0.00 0.00 0.00 0.00 0.00 0.00 96.20 0.00 未知 普林斯顿大学
Amazon Nova Pro 0.00 85.90 0.00 76.60 0.00 89.00 0.00 0.00 未知 亚马逊
OpenAI o3-mini (medium) 0.00 0.00 0.00 0.00 0.00 0.00 0.00 67.40 未知 OpenAI
Gemini 2.5 Flash 0.00 0.00 0.00 0.00 78.30 0.00 0.00 63.40 未知 Google Deep Mind
GPT-4.1 nano 0.00 80.10 0.00 0.00 50.30 0.00 0.00 0.00 未知 OpenAI
GPT-4.1 mini 0.00 87.50 0.00 0.00 65.00 0.00 0.00 0.00 未知 OpenAI
OpenAI o3-mini (high) 0.00 86.90 0.00 97.90 79.70 97.60 97.90 69.50 未知 OpenAI
Kimi k1.5 (Short-CoT) 0.00 87.40 0.00 0.00 0.00 0.00 94.60 0.00 未知 Moonshot AI
Claude Sonnet 3.7-64K Extended Thinking 0.00 0.00 0.00 0.00 84.80 0.00 96.20 0.00 未知 Anthropic
Grok 3 0.00 0.00 0.00 0.00 80.20 0.00 0.00 70.60 未知 xAI
Grok 3 mini 0.00 0.00 0.00 0.00 65.00 0.00 0.00 0.00 未知 xAI
Grok-3 mini - Reasoning 0.00 0.00 0.00 0.00 84.00 0.00 0.00 0.00 未知 xAI
Grok-3 - Reasoning Beta 0.00 0.00 0.00 0.00 84.60 0.00 0.00 79.40 未知 xAI
Claude Sonnet 3.7 0.00 0.00 0.00 0.00 68.00 0.00 82.20 0.00 未知 Anthropic
QwQ-Max-Preview 0.00 0.00 0.00 0.00 0.00 0.00 0.00 65.60 未知 阿里巴巴
Kimi-k1.6-IOI 0.00 0.00 0.00 0.00 0.00 0.00 0.00 65.90 未知 Moonshot AI
Kimi-k1.6-IOI-high 0.00 0.00 0.00 0.00 0.00 0.00 0.00 73.80 未知 Moonshot AI
MMLU Pro
91.04
MMLU
91.80
GSM8K
0.00
MATH
96.40
GPQA Diamond
77.30
HumanEval
0.00
MATH-500
96.40
LiveCodeBench
71.00
MMLU Pro
86.10
MMLU
0.00
GSM8K
0.00
MATH
0.00
GPQA Diamond
71.40
HumanEval
0.00
MATH-500
90.70
LiveCodeBench
46.40
MMLU Pro
85.60
MMLU
0.00
GSM8K
0.00
MATH
0.00
GPQA Diamond
83.30
HumanEval
0.00
MATH-500
0.00
LiveCodeBench
0.00
MMLU Pro
84.00
MMLU
90.80
GSM8K
0.00
MATH
0.00
GPQA Diamond
71.50
HumanEval
0.00
MATH-500
97.30
LiveCodeBench
65.90
MMLU Pro
82.20
MMLU
0.00
GSM8K
0.00
MATH
0.00
GPQA Diamond
73.70
HumanEval
0.00
MATH-500
95.00
LiveCodeBench
49.40
MMLU Pro
81.20
MMLU
0.00
GSM8K
0.00
MATH
0.00
GPQA Diamond
68.40
HumanEval
0.00
MATH-500
94.00
LiveCodeBench
49.20
MMLU Pro
80.60
MMLU
0.00
GSM8K
0.00
MATH
0.00
GPQA Diamond
81.40
HumanEval
0.00
MATH-500
0.00
LiveCodeBench
0.00
MMLU Pro
80.50
MMLU
0.00
GSM8K
0.00
MATH
0.00
GPQA Diamond
69.80
HumanEval
0.00
MATH-500
0.00
LiveCodeBench
43.40
MMLU Pro
80.50
MMLU
0.00
GSM8K
0.00
MATH
0.00
GPQA Diamond
66.30
HumanEval
0.00
MATH-500
0.00
LiveCodeBench
0.00
MMLU Pro
80.30
MMLU
85.20
GSM8K
0.00
MATH
0.00
GPQA Diamond
60.00
HumanEval
92.40
MATH-500
90.00
LiveCodeBench
52.00
MMLU Pro
79.10
MMLU
86.50
GSM8K
0.00
MATH
91.80
GPQA Diamond
64.70
HumanEval
0.00
MATH-500
0.00
LiveCodeBench
0.00
MMLU Pro
79.00
MMLU
89.50
GSM8K
0.00
MATH
89.70
GPQA Diamond
57.50
HumanEval
91.00
MATH-500
0.00
LiveCodeBench
32.00
MMLU Pro
77.90
MMLU
88.70
GSM8K
0.00
MATH
75.90
GPQA Diamond
53.60
HumanEval
90.00
MATH-500
75.90
LiveCodeBench
35.10
MMLU Pro
77.90
MMLU
85.70
GSM8K
0.00
MATH
68.50
GPQA Diamond
0.00
HumanEval
90.20
MATH-500
0.00
LiveCodeBench
0.00
MMLU Pro
77.64
MMLU
88.30
GSM8K
0.00
MATH
71.10
GPQA Diamond
59.40
HumanEval
92.00
MATH-500
0.00
LiveCodeBench
0.00
MMLU Pro
76.24
MMLU
0.00
GSM8K
0.00
MATH
0.00
GPQA Diamond
0.00
HumanEval
0.00
MATH-500
0.00
LiveCodeBench
0.00
MMLU Pro
76.10
MMLU
87.90
GSM8K
94.50
MATH
68.50
GPQA Diamond
0.00
HumanEval
73.20
MATH-500
0.00
LiveCodeBench
0.00
MMLU Pro
75.90
MMLU
88.50
GSM8K
0.00
MATH
87.80
GPQA Diamond
59.10
HumanEval
89.00
MATH-500
87.80
LiveCodeBench
34.60
MMLU Pro
75.50
MMLU
87.50
GSM8K
0.00
MATH
76.10
GPQA Diamond
56.00
HumanEval
88.40
MATH-500
0.00
LiveCodeBench
0.00
MMLU Pro
74.30
MMLU
0.00
GSM8K
0.00
MATH
0.00
GPQA Diamond
57.20
HumanEval
0.00
MATH-500
0.00
LiveCodeBench
32.80
MMLU Pro
73.40
MMLU
88.60
GSM8K
0.00
MATH
73.90
GPQA Diamond
49.00
HumanEval
89.00
MATH-500
0.00
LiveCodeBench
30.20
MMLU Pro
68.18
MMLU
0.00
GSM8K
94.39
MATH
0.00
GPQA Diamond
0.00
HumanEval
0.00
MATH-500
0.00
LiveCodeBench
70.70
MMLU Pro
62.90
MMLU
85.50
GSM8K
0.00
MATH
61.20
GPQA Diamond
0.00
HumanEval
0.00
MATH-500
0.00
LiveCodeBench
0.00
MMLU Pro
61.60
MMLU
0.00
GSM8K
0.00
MATH
0.00
GPQA Diamond
0.00
HumanEval
0.00
MATH-500
0.00
LiveCodeBench
0.00
MMLU Pro
58.20
MMLU
79.60
GSM8K
0.00
MATH
50.30
GPQA Diamond
0.00
HumanEval
0.00
MATH-500
0.00
LiveCodeBench
0.00
MMLU Pro
56.33
MMLU
0.00
GSM8K
0.00
MATH
0.00
GPQA Diamond
0.00
HumanEval
0.00
MATH-500
0.00
LiveCodeBench
0.00
MMLU Pro
51.00
MMLU
81.30
GSM8K
0.00
MATH
50.60
GPQA Diamond
35.90
HumanEval
74.10
MATH-500
0.00
LiveCodeBench
0.00
MMLU Pro
0.00
MMLU
0.00
GSM8K
0.00
MATH
0.00
GPQA Diamond
0.00
HumanEval
0.00
MATH-500
96.20
LiveCodeBench
0.00
MMLU Pro
0.00
MMLU
85.90
GSM8K
0.00
MATH
76.60
GPQA Diamond
0.00
HumanEval
89.00
MATH-500
0.00
LiveCodeBench
0.00
MMLU Pro
0.00
MMLU
0.00
GSM8K
0.00
MATH
0.00
GPQA Diamond
0.00
HumanEval
0.00
MATH-500
0.00
LiveCodeBench
67.40
MMLU Pro
0.00
MMLU
0.00
GSM8K
0.00
MATH
0.00
GPQA Diamond
78.30
HumanEval
0.00
MATH-500
0.00
LiveCodeBench
63.40
MMLU Pro
0.00
MMLU
80.10
GSM8K
0.00
MATH
0.00
GPQA Diamond
50.30
HumanEval
0.00
MATH-500
0.00
LiveCodeBench
0.00
MMLU Pro
0.00
MMLU
87.50
GSM8K
0.00
MATH
0.00
GPQA Diamond
65.00
HumanEval
0.00
MATH-500
0.00
LiveCodeBench
0.00
MMLU Pro
0.00
MMLU
86.90
GSM8K
0.00
MATH
97.90
GPQA Diamond
79.70
HumanEval
97.60
MATH-500
97.90
LiveCodeBench
69.50
MMLU Pro
0.00
MMLU
87.40
GSM8K
0.00
MATH
0.00
GPQA Diamond
0.00
HumanEval
0.00
MATH-500
94.60
LiveCodeBench
0.00
MMLU Pro
0.00
MMLU
0.00
GSM8K
0.00
MATH
0.00
GPQA Diamond
84.80
HumanEval
0.00
MATH-500
96.20
LiveCodeBench
0.00
MMLU Pro
0.00
MMLU
0.00
GSM8K
0.00
MATH
0.00
GPQA Diamond
80.20
HumanEval
0.00
MATH-500
0.00
LiveCodeBench
70.60
MMLU Pro
0.00
MMLU
0.00
GSM8K
0.00
MATH
0.00
GPQA Diamond
65.00
HumanEval
0.00
MATH-500
0.00
LiveCodeBench
0.00
MMLU Pro
0.00
MMLU
0.00
GSM8K
0.00
MATH
0.00
GPQA Diamond
84.00
HumanEval
0.00
MATH-500
0.00
LiveCodeBench
0.00
MMLU Pro
0.00
MMLU
0.00
GSM8K
0.00
MATH
0.00
GPQA Diamond
84.60
HumanEval
0.00
MATH-500
0.00
LiveCodeBench
79.40
MMLU Pro
0.00
MMLU
0.00
GSM8K
0.00
MATH
0.00
GPQA Diamond
68.00
HumanEval
0.00
MATH-500
82.20
LiveCodeBench
0.00
MMLU Pro
0.00
MMLU
0.00
GSM8K
0.00
MATH
0.00
GPQA Diamond
0.00
HumanEval
0.00
MATH-500
0.00
LiveCodeBench
65.60
MMLU Pro
0.00
MMLU
0.00
GSM8K
0.00
MATH
0.00
GPQA Diamond
0.00
HumanEval
0.00
MATH-500
0.00
LiveCodeBench
65.90
MMLU Pro
0.00
MMLU
0.00
GSM8K
0.00
MATH
0.00
GPQA Diamond
0.00
HumanEval
0.00
MATH-500
0.00
LiveCodeBench
73.80