HMMT February 2025
- OpenAI
Results
| Model | Score | Source | Human-verified |
|---|---|---|---|
| GPT-5.211 Dec 2025 · OpenAI | 99.4% | Introducing GPT-5.2Reasoning effort set to the maximum available; GPT-5.2 Pro prints 100.0% | Yes |
Benchmark
hmmt.orgHigher is better
Harvard-MIT Mathematics TournamentIntroduced 15 Feb 2025