List your company

Program Synthesis on HumanEval Standard Relaxed (test)

0.988pass@1QualityFlow
0.975520.978760.9820.98524Jan 20, 2025

Evaluation results

MethodLinks
QualityFlowLLM Backbone=Claude Sonnet-3.5-v2, Evaluation Setting=Relaxed2025.010.9880.6
LDB2025.010.982—
QualityFlowLLM Backbone=Claude Sonnet-3.5-v2, Evaluation Setting=Standard2025.010.976—