Question Answering on StrategyQA (out-of-domain)
55.7AccuracySuCo
Evaluation results
| Method | Links | ||
|---|---|---|---|
| SuCo2026.06 | 55.7 | 442 | |
| DeepSeek-R1-Distill2026.06 | 53.3 | 483 | |
| MFT2026.06 | 28 | 213 | |
| Full CoT SFT2026.06 | 22.6 | 742 |
| Method | Links | ||
|---|---|---|---|
| SuCo2026.06 | 55.7 | 442 | |
| DeepSeek-R1-Distill2026.06 | 53.3 | 483 | |
| MFT2026.06 | 28 | 213 | |
| Full CoT SFT2026.06 | 22.6 | 742 |