| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MUC English 4 | THINKTWICE | MUC Score58.32 | 13 | 4d ago | |
| MultiMUC (averaged across languages) | THINKTWICE Qwen 3 (oracle) | F1 Score33.08 | 9 | 4d ago | |
| MUC | THINKTWICE Qwen 3 (oracle) | F1 Score46.48 | 9 | 4d ago | |
| BETTER | THINKTWICE Qwen 3 (oracle) | F1 Score36.74 | 8 | 4d ago | |
| DWIE (test) | REXEL | Coref Score96.05 | 6 | 4d ago | |
| DocRED (E2E split) | REXEL | Coref90.93 | 5 | 4d ago | |
| DWIE | REXEL | Inference Time (s)27 | 3 | 4d ago | |
| DocRED | REXEL | Inference Time (s)18 | 3 | 4d ago | |
| DocRED augmented with ReFinED (E2E) | REXEL | MD Score90.1 | 1 | 4d ago |