Benchmark
HMMT
A dated competition, not a fixed set: each sitting is a different instrument and contamination rises once problems are published.
- Released
- 2025-02-15
- Categories
- math
- Openness
- unknown
- Source
- model_reports
- Reported scores
- 7
Reported scores
model_reports
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| DeepSeek-V4-Flash | DeepSeek | 94.8 | 2026-06-25 | evidence |
| DeepSeek-V4-Pro | DeepSeek | 95.2 | 2026-04-22 | evidence |
| GLM-5 | Z.ai | 96.9 | 2026-02-11 | evidence |
| GLM-5.1 | Z.ai | 94.0 | 2026-04-03 | evidence |
| GLM-5.2 | Z.ai | 94.4 | 2026-06-16 | evidence |
| Qwen3.5-397B-A17B | Qwen | 94.8 | 2026-02-16 | evidence |
| Qwen3.5-397B-A17B | Qwen | 92.7 | 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.