List your company

Code Generation on HumanEval (Pass@k)

19.15Pass@1ANCORA
5.01648.685712.35516.0243Apr 30, 2026

Evaluation results

MethodLinks
ANCORABackbone=Qwen2.5-Coder-3B-Instruct, Evaluation Setting=Test-Time Training, Seed Configuration=Test Dataset, Prompting=0-shot2026.0419.1521.6723.91
PSVBackbone=Qwen2.5-Coder-3B-Instruct, Evaluation Setting=Test-Time Training, Seed Configuration=Test Dataset, Prompting=1-shot2026.0419.0723.4225.16
ANCORABackbone=Qwen2.5-Coder-3B-Instruct, Evaluation Setting=Transfer Learning, Seed Configuration=Dafny2Verus, Prompting=0-shot2026.0417.1920.1621.03
PSVBackbone=Qwen2.5-Coder-3B-Instruct, Evaluation Setting=Transfer Learning, Seed Configuration=Dafny2Verus, Prompting=1-shot2026.0416.1821.6123.13
RFTBackbone=Qwen2.5-Coder-3B-Instruct, Evaluation Setting=Transfer Learning, Seed Configuration=Dafny2Verus, Prompting=1-shot2026.0410.9918.0720.02
AlphaVerusBackbone=Qwen2.5-Coder-3B-Instruct, Evaluation Setting=Transfer Learning, Seed Configuration=Dafny2Verus, Prompting=50-shot2026.047.2415.3818.02
AlphaVerusBackbone=Qwen2.5-Coder-3B-Instruct, Evaluation Setting=Test-Time Training, Seed Configuration=Test Dataset, Prompting=50-shot2026.047.2415.3818.02
RFTBackbone=Qwen2.5-Coder-3B-Instruct, Evaluation Setting=Test-Time Training, Seed Configuration=Test Dataset, Prompting=1-shot2026.045.5612.4614.8