AI benchmarks and leaderboards are different things
Learn the difference between a benchmark, an evaluation run and a leaderboard, and use each to answer the right question.
LLM Stats
HMMT February 2026 is a math competition benchmark based on problems from the Harvard-MIT Mathematics Tournament, testing advanced mathematical problem-solving and reasoning.
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Shown in source observation order, not ranked. Dates retain the precision provided by the source.
| Model | Value | Unit | Protocol | Reported date and basis | Source |
|---|---|---|---|---|---|
| Qwen3.7 Max | 0.971 | Not recorded | Not recorded | 2026-05-19 · model_announcement | LLM Stats |
| DeepSeek-V4-Pro-Max | 0.952 | Not recorded | Not recorded | 2026-04-23 · model_announcement | LLM Stats |
| DeepSeek-V4-Flash-Max | 0.948 | Not recorded | Not recorded | 2026-04-23 · model_announcement | LLM Stats |
| Qwen3.7-Plus | 0.929 | Not recorded | Not recorded | 2026-05-31 · model_announcement | LLM Stats |
| Kimi K2.6 | 0.927 | Not recorded | Not recorded | 2026-04-20 · model_announcement | LLM Stats |
| GLM-5.2 | 0.925 | Not recorded | Not recorded | 2026-06-16 · model_announcement | LLM Stats |
| DeepSeek-V4-Flash-0423 | 0.919 | Not recorded | Not recorded | 2026-04-23 · model_announcement | LLM Stats |
| Qwen3.6 Plus | 0.878 | Not recorded | Not recorded | 2026-04-02 · model_announcement | LLM Stats |
| MAI-Thinking-1 | 0.849 | Not recorded | Not recorded | 2026-06-02 · model_announcement | LLM Stats |
| Qwen3.6-27B | 0.843 | Not recorded | Not recorded | 2026-04-21 · model_announcement | LLM Stats |
| Qwen3.6-35B-A3B | 0.836 | Not recorded | Not recorded | 2026-04-16 · model_announcement | LLM Stats |
| GLM-5.1 | 0.826 | Not recorded | Not recorded | 2026-04-07 · model_announcement | LLM Stats |