Value Modeling on DAPO-Math-17k Qwen3-4B-Instruct-2507 policy (Held-out)
0.689Intra AUC
V0
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.02 | 0.689 | 0.804 | 0.138 | |
2026.02 | 0.512 | 0.304 | 0.474 |
V0
| Method | Links | |||
|---|---|---|---|---|
2026.02 | 0.689 | 0.804 | 0.138 | |
2026.02 | 0.512 | 0.304 | 0.474 |