List your company

Code Verification on MBPP+

76.93Pass@1CVeDRL
48.059655.554863.0570.5452Jan 30, 2026

Evaluation results

MethodLinks
CVeDRLScale=0.6B, Policy Model=GPT-4o-m2026.0176.93
CVeDRLScale=0.6B, Policy Model=GPT-3.52026.0176.21
CodeRMScale=8.0B, Policy Model=GPT-3.52026.0175.98
Llama3.1Scale=70B, Policy Model=GPT-3.52026.0175.87
Qwen3Scale=32B, Policy Model=GPT-3.52026.0175.71
CodeRMScale=8.0B, Policy Model=GPT-4o-m2026.0175.18
Qwen3Scale=32B, Policy Model=GPT-4o-m2026.0175.04
Llama3.1Scale=70B, Policy Model=GPT-4o-m2026.0175.01
Qwen3Scale=0.6B, Policy Model=GPT-4o-m2026.0173.74
CVeDRLScale=0.6B, Policy Model=Llama3 70B2026.0173.6
CodeTScale=-, Policy Model=GPT-4o-m2026.0173.28
Qwen3Scale=0.6B, Policy Model=GPT-3.52026.0172.86
Qwen3Scale=32B, Policy Model=Llama3 70B2026.0172.61
CodeRMScale=8.0B, Policy Model=Llama3 70B2026.0172.53
MBR-EScale=-, Policy Model=GPT-4o-m2026.0172.12
Llama3.1Scale=70B, Policy Model=Llama3 70B2026.0171.77
VanillaScale=-, Policy Model=GPT-4o-m2026.0171.32
MBR-EScale=-, Policy Model=GPT-3.52026.0170.49
Qwen3Scale=0.6B, Policy Model=Llama3 70B2026.0170.19
VanillaScale=-, Policy Model=GPT-3.52026.0170.15
CodeTScale=-, Policy Model=GPT-3.52026.0169.93
CodeTScale=-, Policy Model=Llama3 70B2026.0169.88
MBR-EScale=-, Policy Model=Llama3 70B2026.0169.75
VanillaScale=-, Policy Model=Llama3 70B2026.0169.28
CVeDRLScale=0.6B, Policy Model=Llama3 8B2026.0166.79
CodeRMScale=8.0B, Policy Model=Llama3 8B2026.0166.63
Qwen3Scale=32B, Policy Model=Llama3 8B2026.0165.43
Llama3.1Scale=70B, Policy Model=Llama3 8B2026.0165.24
CodeTScale=-, Policy Model=Llama3 8B2026.0159.17
Qwen3Scale=0.6B, Policy Model=Llama3 8B2026.0151.01
MBR-EScale=-, Policy Model=Llama3 8B2026.0149.98
VanillaScale=-, Policy Model=Llama3 8B2026.0149.17