AI基准测试 - LLM性能评分
来自官方模型卡片和第三方评估的真实基准测试分数。比较166个模型在21个基准测试中的表现--从MMLU和GPQA Diamond到SWE-bench和Arena Elo。按类别、模型类型筛选，在图表和矩阵视图之间切换。
基准测试类别
直接跳转到最强的基准测试集群，而不是从完整矩阵开始。
knowledge
3 个基准测试
Shows how well a model has absorbed factual knowledge during training. Saturating above 90%, so less useful for differentiating frontier models.
reasoning
5 个基准测试
One of the best discriminators between models. Scores range widely (40-85%), making it highly informative for comparing reasoning ability.
math
3 个基准测试
Tests genuine mathematical reasoning, not just pattern matching. Reasoning models (o1, R1) dramatically outperform standard models here.
coding
6 个基准测试
The most recognized coding benchmark, though becoming saturated above 90%. Evidence of training data contamination in some models.
instruction
2 个基准测试
Measures instruction-following precision, critical for production applications. Models that score well here are more reliable in structured tasks.
arena
2 个基准测试
The most trusted 'vibes-based' benchmark — reflects real human preferences, not just academic metrics. Widely considered the most meaningful overall ranking.
Massive Multitask Language Understanding
Tests broad knowledge across 57 academic subjects (STEM, humanities, social sciences) with 16,000 multiple-choice questions. The most widely-cited LLM benchmark.
Why it matters
Shows how well a model has absorbed factual knowledge during training. Saturating above 90%, so less useful for differentiating frontier models.
MMLU Scores (54 models)
How to Read This Page
Performance Tiers
Model Types
Saturated benchmarks have top models clustered above 90%, making them less useful for comparison.
Scores sourced from official model cards, technical reports, and third-party evaluations (Artificial Analysis, LMSYS Arena). Last updated: 2026-08-10T18:30:07.477Z. Some scores are approximate.
相关页面
AI基准测试是衡量AI模型在特定任务上表现的标准化测试。常见基准测试包括MMLU（通用知识）、SWE-bench（编程）、GPQA（科学推理）、MATH-500（数学）、Arena Elo（人类偏好）和HumanEval（代码生成）。
没有单一基准测试能捕捉全貌。MMLU测试知识广度，SWE-bench测试现实世界编程能力，Arena Elo反映人类偏好。我们建议综合查看多个基准测试，这就是为什么我们的综合评分权衡了多个维度。
我们的基准测试数据每小时从服务商API和社区评估中刷新。新的基准测试会在成为行业标准后添加。Arena Elo评分根据用户投票持续更新。
基准测试是有用的指标但不是完美的预测器。在MMLU上得分高的模型不一定最适合创意写作，SWE-bench高分也不保证更快的编程辅助。现实世界表现取决于您的具体使用场景、提示工程和集成方法。