| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| WSC | UPA | Accuracy98.5 | 116 | 1mo ago | |
| CoNLL English 2012 (test) | MUC F1 Score88 | 114 | 4mo ago | ||
| Winogrande | ReTeX | Accuracy95 | 72 | 29d ago | |
| GAP (test) | longdoc | Overall F189.9 | 53 | 4mo ago | |
| OntoNotes | GPT-4 | MUC93.7 | 46 | 2mo ago | |
| Winograd WSC273 (test) | Fine-tuned SOTA | Accuracy90.1 | 34 | 4mo ago | |
| WSC | DisambiguSLM | Accuracy@185.2 | 33 | 2mo ago | |
| CoreRes | Accuracy94.79 | 33 | 4mo ago | ||
| LitBank (test) | ImCoref-CeS | Avg. F181.8 | 30 | 2mo ago | |
| LitBank 1.0 (test) | longdoc | CoNLL F181 | 27 | 4mo ago | |
| XWinograd | LANG | Accuracy79.9 | 26 | 2mo ago | |
| SIMMC 2.1 | Qwen3 | Precision59.98 | 22 | 2mo ago | |
| WSC | HIZOO | Loss0.02 | 20 | 1mo ago | |
| CLUEWSC | C-DPO | EM90.98 | 20 | 2mo ago | |
| WSC (test) | PromptAgent | Accuracy82.7 | 19 | 1mo ago | |
| XWinograd French | EuroLM | Score69.9 | 18 | 3mo ago | |
| Winograd | PaLM 2-M | Accuracy90.5 | 18 | 4mo ago | |
| English OntoNotes 5.0 (test) | MUC Precision88.6 | 18 | 4mo ago | ||
| CIN (test) | MUC Recall49.67 | 17 | 1mo ago | ||
| CoNLL 2012 | Average F183.1 | 17 | 4mo ago | ||
| Winogender | GIFT | Accuracy64.72 | 15 | 1mo ago | |
| LitBank 1.0 (dev) | U-MEM | CoNLL F180.5 | 15 | 4mo ago | |
| Winogrande XL | T0-11B | Accuracy60.5 | 13 | 4mo ago | |
| WSC | KiC-Large | Accuracy65.4 | 13 | 4mo ago | |
| OntoNotes 5.0 (dev) | Wu et al. | CoNLL F183.4 | 13 | 4mo ago |