Reasoning on ZLB (test)
38.3Accuracy
Correctness Only
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.02 | 38.3 | 65.7 | |
2026.02 | 35.7 | 70.1 | |
2026.02 | 33.5 | 66.3 | |
2026.02 | 32.6 | 67.3 | |
2026.02 | 32.3 | 61.7 | |
2026.02 | 31.8 | 68.9 | |
2026.02 | 30.6 | 64.3 | |
2026.02 | 28.9 | 70.6 | |
2026.02 | 27.8 | 79.5 | |
2026.02 | 27.4 | 61.6 | |
2026.02 | 26.9 | 62.2 | |
2026.02 | 26.4 | 63.1 | |
2026.02 | 26.3 | 65 | |
2026.02 | 24.1 | 70.8 |