| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| AVeriTeC (test) | causal explanation-based verdict prediction system | Precision54 | 4 | 4mo ago | |
| CovidFact | CREDENCE-decomp | Accuracy71.2 | 3 | 1mo ago | |
| SciFact | CREDENCE-decomp | Accuracy79.9 | 3 | 1mo ago | |
| LIAR-PLUS | CREDENCE-decomp | Accuracy67 | 3 | 1mo ago | |
| PubHealth | CREDENCE-decomp | Accuracy69.91 | 3 | 1mo ago | |
| FEVER | CREDENCE-decomp | Accuracy89.98 | 3 | 1mo ago | |
| Factors | CAAFC | Macro F170.8 | 3 | 2mo ago | |
| Coverbench | CAAFC | Macro F185.8 | 3 | 2mo ago | |
| AVeriTeC | CAAFC | Macro F1 Score77.6 | 3 | 2mo ago | |
| RSS Reasoner-Specific (test) | causal explanation-based verdict prediction system | Precision55 | 2 | 4mo ago |