Reasoning on BBH, GPQA, and MuSR Suite
83.4BBH
Qwen3-14B
Updated 4d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.01 | 83.4 | 49.8 | 57.7 | 63.6 | |
2026.01 | 79 | 39.8 | 58.5 | 59.1 | |
2026.01 | 77.7 | 33.5 | 51.9 | 54.4 | |
2026.01 | 60.3 | 21.6 | 50.3 | 44.1 | |
2026.01 | 50.1 | 33.1 | 51.2 | 44.8 | |
2026.01 | 46.4 | 28.1 | 49.7 | 41.4 | |
2026.01 | 44.5 | 26.6 | 51.7 | 40.9 |