Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Pearson Correlation with Human Evaluation on HOWTOBENCH English
Loading...
0.85
Completion Correlation
ROUGE-L
0.642
0.696
0.75
0.804
Apr 21, 2026
Completion Correlation
Guide Correlation
Openness Correlation
Overall Correlation
Updated 1mo ago
Evaluation Results
Method
Method
Links
Completion Correlation
Guide Correlation
Openness Correlation
Overall Correlation
ROUGE-L
2026.04
0.85
0.34
0.48
0.52
ToW
2026.04
0.82
0.82
0.86
0.85
Rubrics
2026.04
0.76
0.85
0.81
0.81
BLEU-1
2026.04
0.74
0.65
0.69
0.71
Auto Plan
2026.04
0.65
0.71
0.54
0.69
Feedback
Search any
task
Search any
task