Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Functional Diversity Evaluation on Functional Diversity Taxonomy Study All Categories
Loading...
0.94
Spearman Correlation
Claude-4-Sonnet
0.2536
0.4318
0.61
0.7882
Sep 25, 2025
Spearman Correlation
Inter-rater Agreement
Updated 1mo ago
Evaluation Results
Method
Method
Links
Spearman Correlation
Inter-rater Agreement
Claude-4-Sonnet
Taxonomy-guided=true
2025.09
0.94
-
Gemini-2.5-Flash
Taxonomy-guided=true
2025.09
0.92
-
GPT-4o
Taxonomy-guided=true
2025.09
0.9
-
Embedding Diversity
2025.09
0.78
-
Vocabulary Diversity
2025.09
0.63
-
Novelty-Bench Functional Diversity
2025.09
0.6
-
Compression Diversity
2025.09
0.28
-
Human Inter-Rater Agreement
2025.09
-
90
Feedback
Search any
task
Search any
task