Mathematical Proof Reasoning on IMO-ProofBench-Advanced Novel (22 problems)
55.7Mask-Proof Avg@4
Gemini 2.5 Pro
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.06 | 55.7 | 15.9 | |
2026.06 | 44.3 | 15.1 | |
2026.06 | 43.2 | 19.8 | |
2026.06 | 34.1 | 7.1 | |
2026.06 | 33 | 8.7 | |
2026.06 | 30.7 | 6.3 | |
2026.06 | 23.9 | 4 |