| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| GPQA | M2CL | Accuracy78.9 | 44 | 1mo ago | |
| GPQA Diamond | HEART | Accuracy98.74 | 40 | 8d ago | |
| SuperGPQA | Rule+CER | Pass@136 | 14 | 2mo ago | |
| GPQA-D | GeoFaith | Accuracy49.5 | 12 | 7d ago | |
| BEHEMOTH GPQA Diamond (out-of-distribution) | GEPA | Accuracy50 | 6 | 1mo ago | |
| GPQA diamond | Pass@1078.29 | 6 | 3mo ago | ||
| GPQA main | Pass@1076.7 | 6 | 3mo ago | ||
| GPQA | Phi-4-mini + Mistral3-3B | Pass@170.18 | 5 | 3mo ago | |
| SuperGPQA | RealSafe | Accuracy33.6 | 3 | 3mo ago |