Arithmetic Reasoning on Countdown 512 tokens
62.1Pass@1
d-TreeRPO
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2025.12 | 62.1 | |
2025.12 | 60.6 | |
2025.12 | 60.2 | |
2025.12 | 58.7 | |
2025.12 | 56.3 | |
2025.12 | 54.8 | |
2025.12 | 53.4 | |
2025.12 | 52.6 | |
2025.12 | 49.1 | |
2025.12 | 48.2 | |
2025.12 | 46.1 | |
2025.12 | 41.4 | |
2025.12 | 37.1 | |
2025.12 | 18 | |
2025.12 | 16 |