List your company

Verus Code Generation on MBPP

44.11Pass@1ANCORA
2.218813.094423.9734.8456Apr 30, 2026

Evaluation results

MethodLinks
ANCORABackbone=Qwen2.5-Coder-3B-Instruct, Evaluation Setting=Test-Time Training, Seed Configuration=Test Dataset, Prompting=0-shot2026.0444.1146.6247.91
PSVBackbone=Qwen2.5-Coder-3B-Instruct, Evaluation Setting=Test-Time Training, Seed Configuration=Test Dataset, Prompting=1-shot2026.0436.7851.2253.67
ANCORABackbone=Qwen2.5-Coder-3B-Instruct, Evaluation Setting=Transfer Learning, Seed Configuration=Dafny2Verus, Prompting=0-shot2026.0436.238.4939.94
PSVBackbone=Qwen2.5-Coder-3B-Instruct, Evaluation Setting=Transfer Learning, Seed Configuration=Dafny2Verus, Prompting=1-shot2026.0425.2538.3241.51
RFTBackbone=Qwen2.5-Coder-3B-Instruct, Evaluation Setting=Transfer Learning, Seed Configuration=Dafny2Verus, Prompting=1-shot2026.0410.9926.0331.19
AlphaVerusBackbone=Qwen2.5-Coder-3B-Instruct, Evaluation Setting=Transfer Learning, Seed Configuration=Dafny2Verus, Prompting=50-shot2026.046.4818.3624.57
AlphaVerusBackbone=Qwen2.5-Coder-3B-Instruct, Evaluation Setting=Test-Time Training, Seed Configuration=Test Dataset, Prompting=50-shot2026.046.4818.3624.57
RFTBackbone=Qwen2.5-Coder-3B-Instruct, Evaluation Setting=Test-Time Training, Seed Configuration=Test Dataset, Prompting=1-shot2026.043.8314.5622.64