Tibetan · structure_f1
Table-of-contents extraction
Benchmark toc-extraction/bo 2.0.0 · 85 items
- – sabcad-outlinerreference 0.903+0.057
- – sabcad-outliner+scriptreference 0.899+0.054
- 1 TOC extraction (sa-bcad method)best skill 0.893+0.047
- 2 TOC extraction (GEPA-optimized)challenger 0.886+0.041
- – No skill (plain prompt) 0.846before
- – sabcad-outlinerreference 0.859+0.119
- – sabcad-outliner+scriptreference 0.831+0.090
- 1 TOC extraction (GEPA-optimized)challenger 0.824+0.084
- 2 TOC extraction (sa-bcad method)best skill 0.823+0.083
- – No skill (plain prompt) 0.741before
- – sabcad-outliner+scriptreference 0.968+0.017
- 1 TOC extraction (sa-bcad method)best skill 0.962+0.011
- 2 TOC extraction (GEPA-optimized)challenger 0.949-0.002
- – sabcad-outlinerreference 0.946-0.005
- – No skill (plain prompt) 0.951before

BuddhistAI