IMO-AnswerBench — leaderboard
International Mathematical Olympiad answer benchmark evaluating final-answer correctness on high-difficulty olympiad-style mathematical problems.
Metric: Score (self-reported). Source: benchmarklist.com. Status: saturation imminent. 14 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V4 Flash | 91.1 |
| 2 | GLM-5.2 | 91 |
| 3 | Qwen 3.7 Max (Max) | 90 |
| 4 | DeepSeek V4 Pro | 89.8 |
| 5 | Nemotron 3 Ultra | 88.6 |
| 6 | Qwen 3.7 Plus | 86 |
| 7 | Qwen 3.6 Plus | 83.8 |
| 8 | GLM-5.1 | 83.8 |
| 9 | Claude Opus 4.8 | 83.5 |
| 10 | Qwen 3.5 397B A17B | 83.1 |
| 11 | Gemini 3.1 Pro (Preview) | 81 |
| 12 | Claude Opus 4.6 (Max) | 75.3 |
| 13 | MiniMax-M2.7 | 68.3 |
Interactive version: theaggregate.ai/benchmark?slug=imo-answerbench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.