Benchmark
AIME
pass@k, majority vote and Python tool access each shift this by double digits.
- Released
- 2024-02-01
- Categories
- math
- Openness
- unknown
- Source
- model_reports
- Reported scores
- 10
Reported scores
model_reports
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Claude Opus 4 | Anthropic | 75.5 | 2025-05-22 | evidence |
| Claude Sonnet 4 | Anthropic | 70.5 | 2025-05-22 | evidence |
| DeepSeek-R1 | DeepSeek | 79.8 | 2025-01-22 | evidence |
| DeepSeek-V3 | DeepSeek | 39.2 | 2024-12-27 | evidence |
| Gemma 4 (31B) | 89.2 | 2026-03-11 | evidence | |
| GLM-5 | Z.ai | 92.7 | 2026-02-11 | evidence |
| GLM-5.1 | Z.ai | 95.3 | 2026-04-03 | evidence |
| GLM-5.2 | Z.ai | 99.2 | 2026-06-16 | evidence |
| Qwen3-235B-A22B (Thinking) | Qwen | 85.7 | 2025-05-14 | evidence |
| Qwen3.5-397B-A17B | Qwen | 91.3 | 2026-02-16 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.