General Reasoning on TheoremQA (Average@2)
36.3Average@2CoVRL
Evaluation Results
| Method | Links | |
|---|---|---|
| CoVRLBackbone=Qwen2.5-7B-Base2025.12 | 36.3 | |
| RAVRBackbone=Qwen2.5-7B-Base, Algorithm=GRPO2025.12 | 34.8 | |
| RLPRBackbone=Qwen2.5-7B-Base, Algorithm=GRPO2025.12 | 33.5 | |
| VeriFreeBackbone=Qwen2.5-7B-Base, Algorithm=GRPO2025.12 | 33.4 | |
| LaTROBackbone=Qwen2.5-7B-Base, Algorithm=GRPO2025.12 | 32.8 | |
| JLBBackbone=Qwen2.5-7B-Base, Algorithm=GRPO2025.12 | 31.9 | |
| Base ModelBackbone=Qwen2.5-7B-Base2025.12 | 25.2 |