| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Coreference Resolution | GAP (test) | Overall F189.9 | 53 | |
| Puzzle Solving | GAP-5 5x5 (test) | PA30 | 8 | |
| Interatomic Potential Modeling | GAP 17 (test) | RMSE (Energy)8.55 | 7 | |
| Coreference Resolution | GAP Stage 2 1.0 (test) | Male F194.1 | 6 | |
| Coreference Resolution | GAP Stage 1 1.0 (test) | Male F1 Score91.1 | 6 | |
| Coreference Resolution | GAP | Accuracy88.6 | 4 | |
| Coreference Resolution | GAP 5.0 (test) | Masc F190.6 | 4 | |
| People Tracking | GAP | Preference Score74 | 2 | |
| Generalized Assignment Problem | GAP | Approximation Ratio-1 | 1 |