| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| TableBench (test) | Qwen3-4B | Accuracy85.42 | 136 | 2mo ago | |
| RealHitBench | DeepSeek-R1 | Exact Match70.91 | 94 | 3mo ago | |
| LIAR | DisambiguSLM | Accuracy@169 | 33 | 2mo ago | |
| COVID-Fact | OpenAI o1 | Balanced Acc75.9 | 32 | 2mo ago | |
| LIAR | Accuracy79 | 28 | 26d ago | ||
| PubHealth | KG-CRAFTL3.3 | Balanced Accuracy78.66 | 26 | 4mo ago | |
| ExpertQA | ANCHOR | Balanced Accuracy61.1 | 25 | 2mo ago | |
| HealthVer | iPOE-llm | F1-macro68 | 21 | 2mo ago | |
| LIAR-RAW | KG-CRAFT | Precision77.38 | 20 | 4mo ago | |
| FEVEROUS (test) | Trification | Macro F174.72 | 20 | 4mo ago | |
| InFi-Check-FG 1.0 (test) | Llama-3.1-8B-Instruct | PredE18.82 | 18 | 4mo ago | |
| AdvFact | ToE | Accuracy64 | 16 | 26d ago | |
| CheckCOVID | ToE | Accuracy60 | 16 | 26d ago | |
| PolitiFact | ToE | Accuracy72 | 16 | 26d ago | |
| FeLMWk | PCC | F1 (True)0.79 | 16 | 4mo ago | |
| HOVER 4-hop (test) | Trification | Macro F166.23 | 16 | 4mo ago | |
| HOVER 3-hop (test) | Trification | Macro F166.42 | 16 | 4mo ago | |
| HOVER 2-hop (test) | Trification | Macro F175.13 | 16 | 4mo ago | |
| Average across General and Medical Domains | Overall Average73.6 | 15 | 4mo ago | ||
| SCIFact | OpenAI o1 | Balanced Acc90.3 | 15 | 4mo ago | |
| SummEval | Balanced Accuracy77.3 | 15 | 4mo ago | ||
| AggreFact CNN | GraphEval | Balanced Acc69.5 | 15 | 4mo ago | |
| AggreFact Xsum | GPT-4o | Balanced Accuracy76.4 | 15 | 4mo ago | |
| Causal and Downstream Robustness Ablation Suite Averaged over 4 models | HETA | Fact EMΔ3.7 | 14 | 3mo ago | |
| FEVEROUS | F1 Macro89.4 | 14 | 4mo ago |
