Code Verification on MBPP+
76.93Pass@1CVeDRL
Evaluation Results
| Method | Links | |
|---|---|---|
| CVeDRLScale=0.6B, Policy Model=GPT-4o-m2026.01 | 76.93 | |
| CVeDRLScale=0.6B, Policy Model=GPT-3.52026.01 | 76.21 | |
| CodeRMScale=8.0B, Policy Model=GPT-3.52026.01 | 75.98 | |
| Llama3.1Scale=70B, Policy Model=GPT-3.52026.01 | 75.87 | |
| Qwen3Scale=32B, Policy Model=GPT-3.52026.01 | 75.71 | |
| CodeRMScale=8.0B, Policy Model=GPT-4o-m2026.01 | 75.18 | |
| Qwen3Scale=32B, Policy Model=GPT-4o-m2026.01 | 75.04 | |
| Llama3.1Scale=70B, Policy Model=GPT-4o-m2026.01 | 75.01 | |
| Qwen3Scale=0.6B, Policy Model=GPT-4o-m2026.01 | 73.74 | |
| CVeDRLScale=0.6B, Policy Model=Llama3 70B2026.01 | 73.6 | |
| CodeTScale=-, Policy Model=GPT-4o-m2026.01 | 73.28 | |
| Qwen3Scale=0.6B, Policy Model=GPT-3.52026.01 | 72.86 | |
| Qwen3Scale=32B, Policy Model=Llama3 70B2026.01 | 72.61 | |
| CodeRMScale=8.0B, Policy Model=Llama3 70B2026.01 | 72.53 | |
| MBR-EScale=-, Policy Model=GPT-4o-m2026.01 | 72.12 | |
| Llama3.1Scale=70B, Policy Model=Llama3 70B2026.01 | 71.77 | |
| VanillaScale=-, Policy Model=GPT-4o-m2026.01 | 71.32 | |
| MBR-EScale=-, Policy Model=GPT-3.52026.01 | 70.49 | |
| Qwen3Scale=0.6B, Policy Model=Llama3 70B2026.01 | 70.19 | |
| VanillaScale=-, Policy Model=GPT-3.52026.01 | 70.15 | |
| CodeTScale=-, Policy Model=GPT-3.52026.01 | 69.93 | |
| CodeTScale=-, Policy Model=Llama3 70B2026.01 | 69.88 | |
| MBR-EScale=-, Policy Model=Llama3 70B2026.01 | 69.75 | |
| VanillaScale=-, Policy Model=Llama3 70B2026.01 | 69.28 | |
| CVeDRLScale=0.6B, Policy Model=Llama3 8B2026.01 | 66.79 | |
| CodeRMScale=8.0B, Policy Model=Llama3 8B2026.01 | 66.63 | |
| Qwen3Scale=32B, Policy Model=Llama3 8B2026.01 | 65.43 | |
| Llama3.1Scale=70B, Policy Model=Llama3 8B2026.01 | 65.24 | |
| CodeTScale=-, Policy Model=Llama3 8B2026.01 | 59.17 | |
| Qwen3Scale=0.6B, Policy Model=Llama3 8B2026.01 | 51.01 | |
| MBR-EScale=-, Policy Model=Llama3 8B2026.01 | 49.98 | |
| VanillaScale=-, Policy Model=Llama3 8B2026.01 | 49.17 |