| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| TabFact | Human | Accuracy92.1 | 86 | 25d ago | |
| FEVER | COT-SC + VE | Accuracy53.9 | 72 | 2mo ago | |
| FEVER (dev) | ROBERTaBase Flexible (IE1) + MSPP (REk) | Label Accuracy82.1 | 57 | 4mo ago | |
| FEVER (val) | augmented surrogate | True Deferral-Advice Loss0.555 | 48 | 4mo ago | |
| PubMed (test) | EP+SEM_CRIT | Accuracy73.6 | 45 | 2mo ago | |
| FEVER (test) | ProoFVer-SB | LA Score79.47 | 32 | 4mo ago | |
| FEVER | MADARA | Exact Match (EM)93.6 | 30 | 1mo ago | |
| FEVER | InSemRAG | Accuracy87.45 | 30 | 1mo ago | |
| RAWFC | KG-CRAFT | Precision81.63 | 30 | 4mo ago | |
| M2RAG | Ours-top3 | Accuracy70 | 28 | 2mo ago | |
| MINE | Hyper-KGGen+ | Accuracy84.73 | 28 | 4mo ago | |
| LIAR | ERM | F1 Score68.6 | 24 | 3mo ago | |
| FEVER 1.0 (dev) | ProoFVer | Label Accuracy89.07 | 23 | 4mo ago | |
| SciFact (test) | Design B | Accuracy84 | 21 | 1mo ago | |
| FEVER held-out (test) | Accuracy95.1 | 21 | 1mo ago | ||
| DP (test) | Design A rescue | Accuracy69 | 21 | 1mo ago | |
| 5PILS (test) | Design A rescue | Accuracy79.6 | 21 | 1mo ago | |
| InfoTabs (held-out) | GPT-4o | Accuracy79.5 | 21 | 4mo ago | |
| TabFact (held-in) | Gemini-2.5-Pro | Accuracy85.02 | 21 | 4mo ago | |
| AVeriTeC (dev) | ProFact | METEOR (Q-only)46.08 | 20 | 1mo ago | |
| Fact Verification | FES-RAG-top5 | Accuracy73 | 20 | 2mo ago | |
| FEVER | SAVER | EM61.1 | 18 | 3mo ago | |
| FEVER | FLARE | F1 Score53.9 | 18 | 4mo ago | |
| Creak WikiData (test) | KG-Reasoner with Qwen-2.5-7B | Hits@197.45 | 17 | 3mo ago | |
| FactKG | SeleCom | Accuracy67.44 | 17 | 4mo ago |