| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| HL | Best-of-N (N=3) | Accuracy75 | 23 | 4mo ago | |
| Headline | RM-Regen | Accuracy73 | 23 | 4mo ago | |
| LB | RM-Regen | Accuracy60 | 23 | 4mo ago | |
| DRBench (test) | DR-Rubric-14B (BS-2) | Score42.9 | 14 | 1mo ago | |
| GPQA-Chem | KARMA | Accuracy20.4 | 4 | 18d ago | |
| MMLU-Pro Chemistry | KARMA | Accuracy19.5 | 4 | 18d ago | |
| MMLU Chemistry | KARMA | Accuracy (MMLU Chemistry Domain Reasoning)63 | 4 | 18d ago | |
| CSBench Computer Science | Accuracy50.6 | 4 | 18d ago | ||
| MMLU-Pro Computer Science | KARMA | MMLU-Pro CS Domain Reasoning Accuracy25.6 | 4 | 18d ago | |
| MMLU CS (Computer Science) | KARMA | MMLU CS Domain Reasoning Accuracy70.1 | 4 | 18d ago | |
| GPQA Bio | Accuracy (GPQA Bio)70 | 4 | 18d ago | ||
| MMLU-Pro Biomedical | KARMA | Accuracy (MMLU-Pro Biomedical)53.2 | 4 | 18d ago | |
| MMLU Biomedical | KARMA | Accuracy70.2 | 4 | 18d ago | |
| MedQA Biomedical | KARMA | Accuracy54.1 | 4 | 18d ago |