| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| TruthfulQA | Accuracy70.8 | 93 | 3d ago | ||
| TruthfulQA | Aligner | Reliability Score16.9 | 33 | 3d ago | |
| TruthfulQA (test) | PromptCD | MC154.95 | 30 | 3d ago | |
| TruthfulQA medical (test) | BioMistral 7B TIES | Health Score83.6 | 22 | 3d ago | |
| TruthfulQA | IPO | Normalized Accuracy58.76 | 10 | 3d ago | |
| TruthfulQA | Adam-NSCL | TruthfulQA Score54 | 6 | 3d ago |