Out-of-Domain Reasoning on BGQA, CRUX Eval, Strategy QA, and Table Bench
71.1BGQA Accuracy
QwQ-32B-Preview
Updated 14d ago
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
2026.05 | 71.1 | 65.2 | 88.2 | 51.5 | 69 | |
2026.05 | 68.7 | 35.1 | 95.6 | 46.8 | - | |
2026.05 | 66.8 | 57 | 92 | 43.8 | 64.9 | |
2026.05 | 58.3 | 59.6 | 88.8 | 34.2 | - | |
2026.05 | 53 | 58.1 | 91.3 | 43.2 | 61.4 | |
2026.05 | 51.3 | 28 | 85.3 | 36.2 | 50.2 | |
2026.05 | 50.3 | 38.5 | 92.2 | 32.4 | 53.4 | |
2026.05 | 50.2 | 46 | 88.2 | 32.3 | 54.2 | |
2026.05 | 49 | 11.1 | 84.4 | 34.2 | 44.7 |