Math Reasoning on AIME 2024 (Score %)
40AIME 2024 ScoreSoft-RLVR
Evaluation results
| Method | Links | |
|---|---|---|
| Soft-RLVRVerifier=GPT-OSS-120B, Checklist source=DeepSeek R1, Training step=5002026.05 | 40 | |
| Soft-RLVRVerifier=GPT-OSS-20B, Checklist source=DeepSeek R1, Training step=5002026.05 | 39.33 | |
| Oracle rule-basedReward=Oracle rule-based, Training step=5002026.05 | 36.83 | |
| Command R7B (No RL)Reward=None (Initial Policy), Training step=5002026.05 | 35.67 |