← Benchmarks
HMMT 2025
Harvard-MIT Mathematics Tournament 2025 - A prestigious student-organized mathematics competition for high school students featuring two tournaments (November 2025 at MIT and February 2026 at Harvard) with individual tests, team rounds, and guts rounds
id hmmt-2025 · max 1 · 33 models reported
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 Pro OpenAI | 1.00 |
| 2 | GPT-5.2 OpenAI | 0.99 |
| 3 | DeepSeek-V3.2-Speciale DeepSeek · open | 0.99 |
| 4 | Kimi K2-Thinking-0905 Moonshot AI · open | 0.97 |
| 5 | Qwen3.6 Plus Alibaba Cloud / Qwen Team | 0.97 |
| 6 | Kimi K2.5 Moonshot AI · open | 0.95 |
| 7 | Qwen3.5-397B-A17B Alibaba Cloud / Qwen Team · open | 0.95 |
| 8 | Nemotron 3 Super (120B A12B) NVIDIA · open | 0.95 |
| 9 | GLM-5.2 Zhipu AI · open | 0.94 |
| 10 | GLM-5.1 Zhipu AI · open | 0.94 |
| 11 | Qwen3.6-27B Alibaba Cloud / Qwen Team · open | 0.94 |
| 12 | GPT-5 OpenAI | 0.93 |
| 13 | Grok 4 Fast xAI | 0.93 |
| 14 | Qwen3.5-27B Alibaba Cloud / Qwen Team · open | 0.92 |
| 15 | Qwen3.5-122B-A10B Alibaba Cloud / Qwen Team · open | 0.91 |
| 16 | Qwen3.6-35B-A3B Alibaba Cloud / Qwen Team · open | 0.91 |
| 17 | DeepSeek-V3.2 DeepSeek · open | 0.90 |
| 18 | DeepSeek-V3.2 (Thinking) DeepSeek · open | 0.90 |
| 19 | Qwen3.5-35B-A3B Alibaba Cloud / Qwen Team · open | 0.89 |