Mathematical Reasoning on SAT-Math (Average@32)
97.1Average@32CoVRL
Evaluation Results
| Method | Links | |
|---|---|---|
| CoVRLBackbone=Qwen2.5-7B-Base2025.12 | 97.1 | |
| RAVRBackbone=Qwen2.5-7B-Base, Algorithm=GRPO2025.12 | 94.1 | |
| RLPRBackbone=Qwen2.5-7B-Base, Algorithm=GRPO2025.12 | 93.8 | |
| JLBBackbone=Qwen2.5-7B-Base, Algorithm=GRPO2025.12 | 93.7 | |
| VeriFreeBackbone=Qwen2.5-7B-Base, Algorithm=GRPO2025.12 | 93.3 | |
| LaTROBackbone=Qwen2.5-7B-Base, Algorithm=GRPO2025.12 | 90.1 | |
| Base ModelBackbone=Qwen2.5-7B-Base2025.12 | 76.5 |