| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| PIQA | Accuracy92.93 | 329 | 2d ago | ||
| PIQA (val) | Mistral-v0.1 | Accuracy83 | 113 | 3d ago | |
| PIQA | Qwen2-57B-A14B | Accuracy81.23 | 41 | 3d ago | |
| PIQA | AutoPrompt | Delta Accuracy0 | 24 | 3d ago | |
| PIQA (test) | UL20B | Accuracy90.7 | 24 | 3d ago | |
| PIQA | LinFTPL | Mean Per-Step Regret0.152 | 15 | 3d ago | |
| PIQA | Llama 3.1 8B | Accuracy91 | 12 | 3d ago | |
| PIQA | OPT-IML 175B | Accuracy (0-shot)79.8 | 6 | 3d ago | |
| PIQA (val test) | LLaDA (Base) | Accuracy79.42 | 5 | 3d ago | |
| PIQA | TBDF | Average Relative Improvement1.89 | 3 | 3d ago | |
| PIQA | Flexora | Time (h)3.87 | 2 | 3d ago |