| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| DAPO-Math-17k Qwen2.5-7B-Instruct policy (Held-out) | V0 | Intra AUC0.693 | 2 | 1mo ago | |
| DAPO-Math-17k Qwen3-4B-Instruct-2507 policy (Held-out) | V0 | Intra AUC0.689 | 2 | 1mo ago | |
| DAPO-Math-17k DeepSeek-R1-Distill-Qwen-1.5B policy (Held-out) | V0 | Intra AUC71 | 2 | 1mo ago |