Math Problem Solving on 200 IMO-level math problems IMO-AnswerBench, IMO-ProofBench, ArXivMath (test)
50.6Pass@1 Accuracy
Meta-Harness
Updated 18d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.03 | 50.6 | |
2026.03 | 48.9 | |
2026.03 | 47.6 | |
2026.03 | 47.2 | |
2026.03 | 46.9 | |
2026.03 | 46.7 | |
2026.03 | 46.6 | |
2026.03 | 46.3 | |
2026.03 | 42.6 | |
2026.03 | 42.3 | |
2026.03 | 41.8 | |
2026.03 | 40.4 | |
2026.03 | 38.8 | |
2026.03 | 38.1 | |
2026.03 | 37.5 | |
2026.03 | 37.1 | |
2026.03 | 34.9 | |
2026.03 | 34.4 | |
2026.03 | 34.1 | |
2026.03 | 32.8 | |
2026.03 | 32.2 | |
2026.03 | 31.7 | |
2026.03 | 31.3 | |
2026.03 | 31.1 | |
2026.03 | 31 | |
2026.03 | 30.4 | |
2026.03 | 30.2 | |
2026.03 | 29.2 | |
2026.03 | 28.8 | |
2026.03 | 28.6 | |
2026.03 | 28.3 | |
2026.03 | 27.1 | |
2026.03 | 24.5 | |
2026.03 | 24.5 | |
2026.03 | 23.1 | |
2026.03 | 23 |