Benchmark
HMMT Benchmark
What is 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
- Evaluates
- math
- Openness
- unknown
- Importer
- Model reports
- Reported scores
- 10
Source provenance
- Original evidence https://www.hmmt.org/
HMMT links
- Website https://www.hmmt.org/
HMMT results and 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 |
| Seed2.0 Lite | ByteDance | 86.5 | 2026-02-14 | evidence |
| Seed2.0 Mini | ByteDance | 77.8 | 2026-02-14 | evidence |
| Seed2.0 Pro | ByteDance | 97.3 | 2026-02-14 | 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.
Which sources cite HMMT?
- DeepSeek-V4 DeepSeek, 2026-06-25
- GLM-5.2 Z.ai, 2026-06-16
- DeepSeek-V4-Pro DeepSeek, 2026-04-22
- GLM-5.1 Z.ai, 2026-04-03
- Qwen3.5-397B-A17B Qwen, 2026-02-16
- Seed2.0 (Pro / Lite / Mini) ByteDance, 2026-02-14
- GLM-5 Z.ai, 2026-02-11