HMMT 2025
Progress Over Time
Interactive timeline showing model performance evolution on HMMT 2025
State-of-the-art frontier
Open
Proprietary
HMMT 2025 Leaderboard
33 models
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  OpenAI | — | — | — | ||
| 2 | OpenAI | — | 400K | $1.75 / $14.00 | ||
| 3 |  DeepSeek | 685B | — | — | ||
| 4 |  Moonshot AI | 1.0T | — | — | ||
| 5 |  Alibaba Cloud / Qwen Team | — | 1.0M | $0.50 / $3.00 | ||
| 6 | Moonshot AI | 1.0T | — | — | ||
| 7 | Alibaba Cloud / Qwen Team | 397B | — | — | ||
| 8 | 120B | — | — | |||
| 9 |  Zhipu AI | 753B | 1.0M | $0.95 / $3.00 | ||
| 10 | Zhipu AI | 754B | 200K | $1.40 / $4.40 | ||
| 11 | Alibaba Cloud / Qwen Team | 28B | 262K | $0.60 / $3.60 | ||
| 12 |  xAI | — | 2.0M | $0.20 / $0.50 | ||
| 12 | OpenAI | — | — | — | ||
| 14 | Alibaba Cloud / Qwen Team | 27B | 262K | $0.30 / $2.40 | ||
| 15 | Alibaba Cloud / Qwen Team | 122B | — | — | ||
| 16 | Alibaba Cloud / Qwen Team | 35B | — | — | ||
| 17 | DeepSeek | 685B | — | — | ||
| 17 | DeepSeek | 685B | — | — | ||
| 19 | Alibaba Cloud / Qwen Team | 35B | — | — | ||
| 20 | OpenAI | — | 400K | $0.25 / $2.00 | ||
| 21 |  Sarvam AI | 105B | — | — | ||
| 22 |  Xiaomi | 309B | — | — | ||
| 23 | DeepSeek | 685B | — | — | ||
| 24 | Alibaba Cloud / Qwen Team | 9B | — | — | ||
| 25 | DeepSeek | 671B | 131K | $0.55 / $2.19 | ||
| 26 | OpenAI | — | — | — | ||
| 27 | Alibaba Cloud / Qwen Team | 4B | — | — | ||
| 28 | Sarvam AI | 30B | — | — | ||
| 29 | Moonshot AI | 1.0T | — | — | ||
| 29 | Moonshot AI | 1.0T | — | — | ||
| 31 | OpenAI | — | 1.0M | $0.40 / $1.60 | ||
| 32 | DeepSeek | 671B | — | — | ||
| 33 | OpenAI | — | 1.0M | $2.00 / $8.00 |
Notice missing or incorrect data?
What is 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
HMMT 2025 is a text benchmark evaluating models on math tasks. LLM Stats tracks 33 models on this benchmark, scored on a 0–1 scale. The current average is 0.8, with the leader at 1.0.
Compare leaders on the best AI for math leaderboards.
Current leaders
GPT-5.2 Pro from OpenAI currently leads the HMMT 2025 leaderboard with a score of 1.000 across 33 evaluated AI models.
FAQ
Common questions about the HMMT 2025 benchmark and leaderboard.