Harvard-MIT Mathematics Tournament November 2025 (HMMT Nov 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 November 2025 HMMT slice for high-end mathematical reasoning comparisons.

Benchmark score on HMMT Nov 2025 — September 27, 2026

We compile the HMMT Nov 2025 rows from provider self-reports and secondary reports. GLM-5 leads the table at 96.9%, followed by Qwen3.6 Plus (94.6%) and GLM-5.2 (94.4%). We do not use these results to rank models overall.

1Open weights

GLM-5

Z.AI

96.9%

Overall 54.45Context 200K

2Proprietary

Qwen3.6 Plus

Alibaba

94.6%

Overall 54.59Context 1M

3Open weights

GLM-5.2

Z.AI

94.4%

Overall 62.52Context 1M

9 modelsMathematicsCurrentDisplay onlyUpdated September 27, 2026

Benchmark score table (9 models)

Score

GLM-5Z.AI · Open weight

96.9%

Qwen3.6 PlusAlibaba · Closed

94.6%

GLM-5.2Z.AI · Open weight

94.4%

GLM-5.1Z.AI · Open weight

94.0%

Claude Opus 4.5Anthropic · Closed

93.3%

Qwen3.5 397BAlibaba · Open weight

92.7%

Kimi K2.5Moonshot AI · Open weight

91.1%

Qwen3.6-27BAlibaba · Open weight

90.7%

Qwen3.6-35B-A3BAlibaba · Open weight

89.1%

Among the reported HMMT Nov 2025 rows, GLM-5 is first at 96.9%. The third row is 2.5 points behind. The broader top-10 range is 7.8 points, so many of the published results sit in a relatively narrow band.

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

About HMMT Nov 2025

Year

2025

Tasks

Competition math problems

Format

Contest mathematics

Difficulty

Olympiad-style mathematics

This row preserves exact provider-table values from the late-2025 HMMT contest cycle. It is useful for spotting whether frontier models generalize across separate contest sets rather than a single annual rollup.

Qwen3.6 launch benchmarks

Freshness and provenance

Version

HMMT Nov 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 Nov 2025 measure?

A November 2025 HMMT slice for high-end mathematical reasoning comparisons.

Which model scores highest on HMMT Nov 2025?

GLM-5 by Z.AI currently leads with a score of 96.9% on HMMT Nov 2025.

How many models are evaluated on HMMT Nov 2025?

9 AI models have been evaluated on HMMT Nov 2025 on BenchLM.

Compare top models on HMMT Nov 2025

GLM-5 vs Qwen3.6 Plus Qwen3.6 Plus vs GLM-5.2 GLM-5.2 vs GLM-5.1 GLM-5.1 vs Claude Opus 4.5

Last updated: September 27, 2026 · BenchLM version HMMT Nov 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.