Mathematics benchmark
HMMT Feb 2025 leaderboard
Harvard-MIT Mathematics Tournament February 2025. Every model the catalog carries a published HMMT Feb 2025 value for, ranked by that value.
CategoryMathematics
MeasureContest mathematics
TasksCompetition math problems
DifficultyOlympiad-style mathematics
Published byQwen3.6 launch benchmarks
A February 2025 HMMT slice used in exact-value provider tables for advanced contest-math reasoning.
HMMT Feb 2025 ranking
10 models with a published HMMT Feb 2025 value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Contest mathematics |
|---|---|---|---|
| 1 |  GLM-5 | Z.AI | 97.5 |
| 2 |  Qwen3.6 Plus | Alibaba | 96.7 |
| 3 |  Kimi K2.5 | Moonshot AI | 95.4 |
| 4 | Qwen3.5 397B | Alibaba | 94.8 |
| 5 | Qwen3.6-27B | Alibaba | 93.8 |
| 6 |  Claude Opus 4.5 | Anthropic | 92.9 |
| 7 | Qwen3.6-35B-A3B | Alibaba | 90.7 |
| 8 |  Granite 4.2 30B | IBM | 89.2 |
| 9 | Granite 4.2 8B | IBM | 78.3 |
| 10 | Granite 4.2 3B | IBM | 66.7 |
Evidence key: Observed
Rows are ordered by the value Qwen3.6 launch benchmarks published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.