Skip to content

Harvard-MIT Mathematics Tournament November 2025

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

12 models

Higher is better.

  1. 1GLM-5Z.AI96.9
  2. 2Qwen3.6 PlusAlibaba94.6
  3. 3GLM-5.2Z.AI94.4
  4. 4GLM-5.1Z.AI94.0
  5. 5Claude Opus 4.5Anthropic93.3
  6. 6Qwen3.5 397BAlibaba92.7
  7. 7Kimi K2.5Moonshot AI91.1
  8. 8Qwen3.6-27BAlibaba90.7
  9. 9Qwen3.6-35B-A3BAlibaba89.1
  10. 10Sarvam 105BSarvam85.8
  11. 11MiniMax M2.7MiniMax81.0
  12. 12Sarvam 30BSarvam74.2
Higher is better. Bar colour: blue proprietary, orange open weights, green other.

About this benchmark

Metric
Contest mathematics
Tasks
Competition math problems
Authors
Qwen (2025)

Scores are as reported by model developers or evaluators and may use different settings (for example reasoning effort or tools). Compare with care.