List your company

Code Verification on MBPP (test)

100Mean Hit RateOracle
53.30465.42777.5589.673Jun 14, 2026

Evaluation results

MethodLinks
OracleModel=Qwen3-8B, beta=10%, err=.558, rho=.1782026.06100—
Cost-Stratified ThresholdingModel=LLaMA3-8B, beta=10%, err=.644, rho=.3012026.0688.217
Cost-Stratified ThresholdingModel=LLaMA3-8B, beta=20%, err=.644, rho=.3012026.0683.715.1
Cost-Stratified ThresholdingModel=LLaMA3-8B, beta=30%, err=.644, rho=.3012026.0680.311
Cost-Stratified ThresholdingModel=LLaMA3-8B, beta=50%, err=.644, rho=.3012026.0672.85.3
Cost-Stratified ThresholdingModel=Qwen3-8B, beta=10%, err=.558, rho=.1782026.0667.13.4
Cost-Stratified ThresholdingModel=Qwen3-8B, beta=20%, err=.558, rho=.1782026.0666.15.1
Cost-Stratified ThresholdingModel=Qwen3-8B, beta=30%, err=.558, rho=.1782026.0666.15.6
MP-StratModel=Qwen3-8B, beta=10%, err=.558, rho=.1782026.0665.6—
ThresholdingModel=Qwen3-8B, beta=10%, err=.558, rho=.1782026.0663.6—
Cost-Stratified ThresholdingModel=Qwen3-8B, beta=50%, err=.558, rho=.1782026.0663.14.3
C+MModel=Qwen3-8B, beta=10%, err=.558, rho=.1782026.0662.2—
Cost-Stratified ThresholdingModel=GPT-4o-mini, beta=30%, err=.528, rho=.1742026.0661.46.7
Cost-Stratified ThresholdingModel=GPT-4o-mini, beta=50%, err=.528, rho=.1742026.0661.23.4
Cost-Stratified ThresholdingModel=GPT-4o-mini, beta=20%, err=.528, rho=.1742026.06616.5
MP-AdaptModel=Qwen3-8B, beta=10%, err=.558, rho=.1782026.0659.7—
Cost-Stratified ThresholdingModel=GPT-4o-mini, beta=10%, err=.528, rho=.1742026.0659.28.1
RandomModel=Qwen3-8B, beta=10%, err=.558, rho=.1782026.0655.1—