Functional Diversity Evaluation on Functional Diversity Taxonomy Study All Categories
0.94Spearman CorrelationClaude-4-Sonnet
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Claude-4-SonnetTaxonomy-guided=true2025.09 | 0.94 | — | |
| Gemini-2.5-FlashTaxonomy-guided=true2025.09 | 0.92 | — | |
| GPT-4oTaxonomy-guided=true2025.09 | 0.9 | — | |
| Embedding Diversity2025.09 | 0.78 | — | |
| Vocabulary Diversity2025.09 | 0.63 | — | |
| Novelty-Bench Functional Diversity2025.09 | 0.6 | — | |
| Compression Diversity2025.09 | 0.28 | — | |
| Human Inter-Rater Agreement2025.09 | — | 90 |