Complex Reasoning on BBH (Accuracy and Performance Gain)
89.14Accuracy (%)
l2-guided Selection
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.06 | 89.14 | 3.9 | |
2026.06 | 88.95 | 4.24 | |
2026.06 | 88.11 | 2.75 | |
2026.06 | 88.01 | 3.17 | |
2026.06 | 87.41 | 3.26 | |
2026.06 | 87.39 | 3.1 | |
2026.06 | 87.3 | 3.11 | |
2026.06 | 87.2 | 2.85 | |
2026.06 | 86.41 | 1.88 | |
2026.06 | 85.92 | 1.31 | |
2026.06 | 85.79 | - | |
2026.06 | 85.79 | - | |
2026.06 | 85.33 | - | |
2026.06 | 85.33 | - | |
2026.06 | 84.81 | - | |
2026.06 | 84.81 | - | |
2026.06 | 84.78 | - | |
2026.06 | 84.78 | - | |
2026.06 | 84.67 | - | |
2026.06 | 84.67 | - | |
2026.06 | 76.75 | 5.38 | |
2026.06 | 74.57 | 2.41 | |
2026.06 | 74.14 | 5.19 | |
2026.06 | 72.83 | - | |
2026.06 | 72.83 | - | |
2026.06 | 72.53 | 2.9 | |
2026.06 | 70.48 | - | |
2026.06 | 70.48 | - |