| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| AmbigQA (val) | Spectrum-Qwen3-14B | PRR69.8 | 90 | 1d ago | |
| NCQA (test) | Llama-3.1-8B | AUROC99.2 | 76 | 1d ago | |
| TriviaQA (val) | latent selective | PRR81.3 | 51 | 1d ago | |
| Euler 2D (test) | Step-doubling | AUROC0.98 | 18 | 6d ago | |
| Oregonator (test) | AUROC79 | 18 | 6d ago | ||
| Ball 3D (test) | Deep ensemble | AUROC81 | 15 | 6d ago | |
| Places365 (val) | AUCPR72.83 | 9 | 1mo ago | ||
| CIFAR-100 (test) | LogitDynamics | AUCPR44.3 | 9 | 1mo ago |