| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Standard Downstream Tasks PIQA, HellaSwag, Winogrande, ARC-Challenge, ARC-Easy | PIQA Zero-Shot Accuracy77.47 | 9 | 9d ago | ||
| Downstream Tasks (ARC-C, ARC-E, H'SWAG, LAM'DA, OPENBKQA, PIQA, W'GRANDE) zero-shot | ASVD | ARC-C Score32.76 | 9 | 1mo ago |