Complex Reasoning on SciFact (val)
71.15Macro-F1EvoPool
Evaluation results
| Method | Links | |
|---|---|---|
| EvoPoolBackbone=gpt-4o-mini2026.06 | 71.15 | |
| LLM annotationBackbone=gpt-4o-mini2026.06 | 70.4 | |
| AlchemistBackbone=gpt-4o-mini2026.06 | 34.38 | |
| DataSculptBackbone=gpt-4o-mini2026.06 | 26.09 |