AI 评测与排行榜,分别告诉你什么
分清评测基准、一次评测运行与排行榜,用它们回答各自适合的问题。
Model reports
Static closed-set multiple choice; contamination risk rises over time.
本站保留来源报告的结果,不代表独立复测。请先核对任务版本、评测协议、分数单位和报告日期;不同运行条件不能直接合并为统一排名。
按来源中的观察顺序展示,顺序不代表排名。日期保留原始精度。
| 模型 | 数值 | 单位 | 协议 | 报告日期与口径 | 来源 |
|---|---|---|---|---|---|
| DeepSeek-R1 | 84.0 | percent | EM | 2025-01-22 · document_publication | DeepSeek-R1 |
| DeepSeek-V3 | 75.9 | percent | EM, 8K output limit | 2024-12-27 · document_publication | DeepSeek-V3 |
| DeepSeek-V4-Pro | 82.9 | percent | non-think | 2026-04-22 · document_publication | DeepSeek-V4-Pro |
| DeepSeek-V4-Pro | 87.1 | percent | think high | 2026-04-22 · document_publication | DeepSeek-V4-Pro |
| DeepSeek-V4-Pro | 87.5 | percent | think max | 2026-04-22 · document_publication | DeepSeek-V4-Pro |
| DeepSeek-V4-Flash | 87.5 | percent | think max | 2026-06-25 · document_publication | DeepSeek-V4 |
| Gemma 4 (31B) | 85.2 | percent | as reported | 2026-03-11 · document_publication | Gemma 4 (31B) |
| Qwen3.5-397B-A17B | 87.8 | percent | thinking (temp 0.6, top_p 0.95, top_k 20) | 2026-02-16 · document_publication | Qwen3.5-397B-A17B |