An advanced benchmark for evaluating complete and logically rigorous proofs generated for difficult Olympiad-level mathematics problems.
Browse the latest scores, model modes, release dates, and parameter sizes for IMO-ProofBench Advanced.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
| Rank | Model | License | |||
|---|---|---|---|---|---|
— |  GPT-5.5 Pro Thinking Level · Extra High | 88.10 | 2026-04-23 | Unknown | Closed |
— |  Gemini 3 Deep Think Thinking Enabled | 76.70 | 2025-12-04 | Unknown | Closed |
— | GPT-5.5 Thinking Level · Extra High | 71.90 | 2026-04-23 | Unknown | Closed |
— |  DeepSeekMath-V2 Thinking Level · High | 61.90 | 2025-11-27 | 685B | Free Commercial |
— | Gemini 3 Pro Thinking Enabled | 30.00 | 2026-02-01 | Unknown | Closed |
— | GPT-5-Pro Thinking Enabled | 28.60 | 2025-08-07 | Unknown | Closed |
— |  Opus 4.5 Thinking Enabled | 23.80 | 2025-11-25 | Unknown | Closed |
— | OpenAI o3 Thinking Enabled | 20.50 | 2025-04-16 | Unknown | Closed |
— | GPT-5 Thinking Enabled | 20.00 | 2025-08-07 | Unknown | Closed |
— |  Grok 4 Thinking Enabled | 18.60 | 2025-07-10 | Unknown | Closed |
— | Gemini 2.5-Pro Thinking Enabled | 17.60 | 2025-06-05 | Unknown | Closed |
— | OpenAI o4 - mini Thinking Level · High | 11.40 | 2025-04-16 | Unknown | Closed |
— |  Qwen3-235B-A22B-Thinking Thinking Enabled | 5.20 | 2025-07-30 | 30.5B | Free Commercial |
— | Claude Sonnet 4 Thinking Enabled | 4.80 | 2025-05-23 | Unknown | Closed |
— | Claude Sonnet 4.5 Thinking Enabled | 4.80 | 2025-09-30 | Unknown | Closed |
— | DeepSeek-V3 Thinking Enabled | 4.30 | 2024-12-26 | 681B | Free Commercial |
— | DeepSeek-R1 Thinking Enabled | 3.80 | 2025-01-20 | 671B | Free Commercial |
— | DeepSeek-R1-0528 Thinking Enabled | 3.80 | 2025-05-28 | 671B | Free Commercial |
— | Claude Opus 4 Thinking Enabled | 2.90 | 2025-05-23 | Unknown | Closed |
