Harvard-MIT Mathematics Tournament February 2025 (HMMT Feb 2025)

We show this table for reference; we do not rank on it.

Data verified September 27, 202634 confirmed releases in the last 30 daysFollow model changes

A February 2025 HMMT slice used in exact-value provider tables for advanced contest-math reasoning.

Benchmark score on HMMT Feb 2025 — September 27, 2026

We compile the HMMT Feb 2025 rows from provider self-reports and secondary reports. GLM-5 leads the table at 97.5%, followed by Qwen3.6 Plus (96.7%) and Kimi K2.5 (95.4%). We do not use these results to rank models overall.

1Open weights

GLM-5

Z.AI

97.5%

Overall 54.45Context 200K

2Proprietary

Qwen3.6 Plus

Alibaba

96.7%

Overall 54.59Context 1M

3Open weights

Kimi K2.5

Moonshot AI

95.4%

Overall 52.96Context 256K

10 modelsMathematicsCurrentDisplay onlyUpdated September 27, 2026

Benchmark score table (10 models)

Score

GLM-5Z.AI · Open weight

97.5%

Qwen3.6 PlusAlibaba · Closed

96.7%

Kimi K2.5Moonshot AI · Open weight

95.4%

Qwen3.5 397BAlibaba · Open weight

94.8%

Qwen3.6-27BAlibaba · Open weight

93.8%

Claude Opus 4.5Anthropic · Closed

92.9%

Qwen3.6-35B-A3BAlibaba · Open weight

90.7%

Granite 4.2 30BIBM · Open weight

89.2%

Granite 4.2 8BIBM · Open weight

78.3%

Granite 4.2 3BIBM · Open weight

66.7%

Among the reported HMMT Feb 2025 rows, GLM-5 is first at 97.5%. The third row is 2.1 points behind. The broader top-10 range is 30.8 points, so the table still separates the published systems.

10 models have been evaluated on HMMT Feb 2025. The benchmark falls in the Mathematics category. HMMT Feb 2025 is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About HMMT Feb 2025

Year

2025

Tasks

Competition math problems

Format

Contest mathematics

Difficulty

Olympiad-style mathematics

BenchLM stores this HMMT monthly slice separately from the aggregate HMMT rows so first-party exact values remain visible without overwriting the broader yearly HMMT reference.

Qwen3.6 launch benchmarks

Freshness and provenance

Version

HMMT Feb 2025 2025

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

Questions

What does HMMT Feb 2025 measure?

A February 2025 HMMT slice used in exact-value provider tables for advanced contest-math reasoning.

Which model scores highest on HMMT Feb 2025?

GLM-5 by Z.AI currently leads with a score of 97.5% on HMMT Feb 2025.

How many models are evaluated on HMMT Feb 2025?

10 AI models have been evaluated on HMMT Feb 2025 on BenchLM.

Compare top models on HMMT Feb 2025

GLM-5 vs Qwen3.6 Plus Qwen3.6 Plus vs Kimi K2.5 Kimi K2.5 vs Qwen3.5 397B Qwen3.5 397B vs Qwen3.6-27B

Last updated: September 27, 2026 · BenchLM version HMMT Feb 2025 2025

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 2,000+ readers.

One email each week. Unsubscribe anytime.