Knowledge-intensive Reasoning on GPQA
38.89Result Score
CPPO
Updated 6d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.04 | 38.89 | 35.35 | |
2026.04 | 38.38 | 37.88 | |
2026.04 | 37.88 | 34.85 | |
2026.04 | 35.86 | 33.33 | |
2026.04 | 35.35 | 34.85 | |
2026.04 | 34.85 | 28.79 | |
2026.04 | 33.33 | 30.81 | |
2026.04 | 30.3 | 29.8 | |
2026.04 | 28.79 | 26.77 | |
2026.04 | 28.79 | 24.24 | |
2026.04 | 26.77 | 23.23 | |
2026.04 | 25.25 | 23.23 | |
2026.04 | 22.73 | 19.7 | |
2026.04 | 19.19 | 16.67 |