| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| GPQA | M2CL | Accuracy95.1 | 243 | 3mo ago | |
| GPQA | GSPO + NSR | Accuracy (GPQA)59.22 | 72 | 1mo ago | |
| GPQA Diamond | Accuracy83 | 72 | 1mo ago | ||
| ARC-C | Qwen3-Next-80B + THINKBRAKE | Accuracy97 | 65 | 1mo ago | |
| GPQA Diamond | Pass@191.9 | 57 | 1mo ago | ||
| GPQA (test) | InjectRLOpt | Accuracy64.44 | 56 | 2mo ago | |
| GPQA-D | Qwen3-Next-80B | Accuracy76.3 | 52 | 2mo ago | |
| GPQA | SwiR | Pass@170.2 | 50 | 3mo ago | |
| GPQA | EAPO | Accuracy (GPQA)54.67 | 43 | 23d ago | |
| GPQA Diam | Policy Split | Accuracy58.9 | 27 | 3mo ago | |
| GPQA | Local Highest | GPQA Score69.4 | 27 | 3mo ago | |
| GPQA diamond | SC | Accuracy72.5 | 25 | 2mo ago | |
| ARC | MENTOR | Accuracy89.6 | 25 | 23d ago | |
| GPQA | Phi | r* Accuracy30.9 | 24 | 2mo ago | |
| GPQA | DTSR | Accuracy69.2 | 18 | 1mo ago | |
| GPQA | Score81.4 | 17 | 4mo ago | ||
| GPQA Diamond | GRPO + RePro | Avg@4 Accuracy44.8 | 17 | 4mo ago | |
| GPQA | DARL | Avg@439.4 | 16 | 4mo ago | |
| ARC Challenge (test) | Genius | Accuracy84.04 | 15 | 4mo ago | |
| GPQA Diamond | Qwen3-32B | GPQA Diamond54.6 | 13 | 2mo ago | |
| MMLU Pro | EAPO | Accuracy66.49 | 12 | 25d ago | |
| GPQA Diamond | DeepSeek-R1-Distill | Response Length (Tokens)6,858 | 12 | 1mo ago | |
| MMLU STEM | DeepSeek-R1-Distill | Response Length (Tokens)1,956 | 12 | 1mo ago | |
| GPQA-D | Pass@159.59 | 12 | 4mo ago | ||
| GPQA Diamond | Format-Adaptive-Answer | AUCOAA71.6 | 11 | 4mo ago |