Competition-level Mathematics and Science Reasoning on OlympiadBench (Accuracy)
22.53Accuracy
Repeated Sampling
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2025.10 | 22.53 | |
2025.10 | 21.87 | |
2025.10 | 18.35 | |
2025.10 | 17.47 | |
2025.10 | 15.27 | |
2025.10 | 12.75 |
Repeated Sampling
| Method | Links | |
|---|---|---|
2025.10 | 22.53 | |
2025.10 | 21.87 | |
2025.10 | 18.35 | |
2025.10 | 17.47 | |
2025.10 | 15.27 | |
2025.10 | 12.75 |