List your company

Guide on HOWTOBENCH

0.85Pearson Correlation (ρ)ToW
-0.2940.0030.30.597Apr 21, 2026

Evaluation results

MethodLinks
ToWCost ($)=7.342026.040.850.760.89
Elaborated RubricSelection=best, Cost ($)=1.312026.040.820.70.82
Elaborated Rubric + SCn=10, Cost ($)=13.172026.040.810.70.8
Auto-PlanSelection=best, Cost ($)=0.892026.040.810.630.77
Elaborated Rubric + SCn=5, Cost ($)=6.532026.040.80.650.78
Auto-Plan + SCn=5, Cost ($)=4.452026.040.790.540.67
Auto-Plan + SCn=10, Cost ($)=8.932026.040.790.590.7
Average scoring (ToW w/o plan)Cost ($)=7.022026.040.780.650.78
Elaborated RubricSelection=worst, Cost ($)=1.312026.040.780.650.78
Auto-PlanSelection=worst, Cost ($)=0.892026.040.780.630.74
BLEU-12026.040.650.540.69
ROUGE-L2026.040.060.140.2
BLEU-rt2026.04-0.25-0.2-0.19