List your company

Uncertainty Estimation on Average Across all subsets

77.3AUROCTop-5 + Tests + Pseudo
49.11656.43363.7571.067Jun 8, 2026

Evaluation results

MethodLinks
Top-5 + Tests + PseudoModel=Qwen3-Coder-30B2026.0677.380.3
Top-5 + Tests + PseudoModel=Qwen3-32B2026.0674.779.2
Generated Tests (FUNC)Model=Qwen3-32B2026.0674.575.9
Generated Tests (FUNC)Model=Qwen3-Coder-30B2026.0673.877
Consistency (VR)Model=Qwen3-32B2026.067076
Consistency (BLEU)Model=Qwen3-Coder-30B2026.0669.273.1
Max EntropyModel=Qwen3-Coder-30B2026.0668.873.4
Top-5 Entropy (LEX)Model=Qwen3-Coder-30B2026.0668.875
Pseudo Consistency (ALGO)Model=Qwen3-Coder-30B2026.0665.178.6
Consistency (BLEU)Model=Qwen3-32B2026.0664.170.6
Pseudo Consistency (ALGO)Model=Qwen3-32B2026.0663.669.3
Mean EntropyModel=Qwen3-Coder-30B2026.0662.368.8
Symb. ClusteringModel=Qwen3-32B2026.0662.270.9
Max ProbabilityModel=Qwen3-Coder-30B2026.066269.6
Consistency (VR)Model=Qwen3-Coder-30B2026.0661.668.5
Mean ProbabilityModel=Qwen3-Coder-30B2026.0660.168.4
Top-5 Entropy (LEX)Model=Qwen3-32B2026.0659.964.3
Symb. ClusteringModel=Qwen3-Coder-30B2026.0656.867.7
Max ProbabilityModel=Qwen3-32B2026.0652.962.2
Mean ProbabilityModel=Qwen3-32B2026.0652.561.9
Mean EntropyModel=Qwen3-32B2026.0650.458.4
Max EntropyModel=Qwen3-32B2026.0650.259.1