HMMT Feb 2026: HMMT February 2026
MathArena benchmark based on the February 2026 Harvard-MIT Mathematics Tournament, cited in Microsoft AI's MAI-Thinking-1 technical report.
Models ranked
5
tracked on this benchmark
Score band
84.9 – 25.8
best → lowest tracked
Snapshot trend
-25.30
Jun 2 → Oct 12 · 3 models
Leaderboard
Tracked models ranked by Score (higher is better).
Notes: Microsoft AI technical report Table 11 result for MAI-Thinking-1.
Notes: Scores from the released-checkpoint "after" table on the Hugging Face model card.
How to read this benchmark
This benchmark scores models where higher is better. Use scores for directional filtering and shortlisting, not universal quality ranking; then validate pricing, context window, provider availability, and fit for your workload.
Trust this score when
- There is a fresh timestamped snapshot (or multiple snapshots) for this benchmark.
- The model list covers the same version family you can actually deploy today.
- Top candidates overlap with your required routing and feature requirements.
Be cautious when
- There is only one benchmark snapshot or the dataset appears stale.
- The benchmark metric direction is opposite of your decision objective.
- The score difference between options is narrow and likely within implementation variance.
Related benchmarks
Last reviewed: Jun 3, 2026