High-stakes specialized classification on Claude9 (val)
44.09Macro F1LLM annotation
Evaluation Results
| Method | Links | |
|---|---|---|
| LLM annotationBackbone=gpt-4o-mini2026.06 | 44.09 | |
| EvoPoolBackbone=gpt-4o-mini2026.06 | 34.61 | |
| DataSculptBackbone=gpt-4o-mini2026.06 | 23.38 | |
| AlchemistBackbone=gpt-4o-mini2026.06 | 16.07 |