MathArena - IMO 2025 — leaderboard
Metric: Accuracy (%). Source: matharena.ai. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Human Expert | 100 |
| 2 | GPT-5 (High) | 38.1 |
| 3 | Gemini 2.5 Pro | 31.55 |
| 4 | O3 (High) | 16.67 |
| 5 | O4 Mini (High) | 14.29 |
| 6 | Grok 4 | 11.9 |
| 7 | DeepSeek R1 0528 | 6.85 |
| 8 | Median Human | 0 |
Interactive version: theaggregate.ai/benchmark?slug=matharena-imo-2025 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.