| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Robustness perturbations | Gemma 2 | Mean Robustness Weighted Average Score85.9 | 6 | 1mo ago | |
| Pascal VOC | Gemma 2 | Result Match (%)90.6 | 6 | 1mo ago | |
| OOD | Qwen 2.5 | Overall Match Accuracy40 | 6 | 1mo ago | |
| Fresh | Gemma 2 | Result Match95.4 | 6 | 1mo ago | |
| BIRD 96 questions (subset) | Schema-First Retrieval | Execution Accuracy93.8 | 2 | 26d ago |