Benchmark
IMOAnswerBench
Final-answer grading on olympiad problems, so it does not check whether the proof reasoning was valid.
- Released
- 2025-09-18
- Categories
- math
- Openness
- unknown
- Source
- model_reports
- Reported scores
- 6
Reported scores
model_reports
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| DeepSeek-V4-Flash | DeepSeek | 88.4 | 2026-06-25 | evidence |
| DeepSeek-V4-Pro | DeepSeek | 89.8 | 2026-04-22 | evidence |
| GLM-5 | Z.ai | 82.5 | 2026-02-11 | evidence |
| GLM-5.1 | Z.ai | 83.8 | 2026-04-03 | evidence |
| GLM-5.2 | Z.ai | 91.0 | 2026-06-16 | evidence |
| Qwen3.5-397B-A17B | Qwen | 80.9 | 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.