Robustness Evaluation on CommonsenseQA
79.07VAcc
DeepSeek-R1-Distill-LLaMA-8B
Updated 1mo ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2025.06 | 79.07 | 26.62 | 52.45 | 66.33 | |
2025.06 | 75.84 | 51.32 | 24.52 | 32.33 | |
2025.06 | 58.31 | 34.6 | 23.71 | 40.67 | |
2025.06 | 51.92 | 16.96 | 34.96 | 67.33 |