| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| SlideVQA | ES EM97.7 | 6 | 3mo ago | ||
| MAUD | RankRAG | Relative Evidence Count3.15 | 4 | 1mo ago | |
| CUAD | RankRAG | Relative Evidence Count5.17 | 4 | 1mo ago | |
| PrivacyQA | RankRAG | Relative Evidence Count3.33 | 4 | 1mo ago | |
| FinQA | RankRAG | Relative Evidence Count1.5 | 4 | 1mo ago | |
| Contract-NLI | SBERT | Relative Evidence Count21.33 | 4 | 1mo ago | |
| QASPER | RankRAG | Relative Evidence Count4 | 4 | 1mo ago | |
| MIR benchmark | Ours | Mean Fitness0.59 | 3 | 26d ago | |
| MAUD | METEORA | F1 Score39 | 3 | 1mo ago | |
| CUAD | METEORA | F1 Score33 | 3 | 1mo ago | |
| PrivacyQA | METEORA | F148 | 3 | 1mo ago | |
| FinQA | METEORA | F1 Score43 | 3 | 1mo ago | |
| Contract-NLI | METEORA | F1 Score51 | 3 | 1mo ago | |
| QASPER | METEORA | F1 Score44 | 3 | 1mo ago |