IMO-Bench — leaderboard
Metric: Advanced ProofBench Accuracy (%). Source: imobench.github.io. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 Pro (xHigh) | 88.1 |
| 2 | Gemini 3 Deep Think | 76.7 |
| 3 | GPT-5.5 (xHigh) | 71.9 |
| 4 | Gemini 3.1 Pro (Preview) | 49 |
| 5 | GPT-5.2 (High) | 35.7 |
| 6 | Gemini 3 Pro | 30 |
| 7 | GPT-5 Pro | 28.6 |
| 8 | Claude Opus 4.5 | 23.8 |
| 9 | Grok 4.1 Fast (Reasoning) | 18.6 |
| 10 | GPT-5.1 | 7.1 |
Interactive version: theaggregate.ai/benchmark?slug=imo-bench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.