Procedural Planning on Macro Average Zero-shot
69.7Macro Accuracy (Zero-shot)GPT-4o-mini
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-4o-miniModel capacity=Frontier (approx. 700B), Input format=Socratic configuration2026.05 | 69.7 | |
| Gemini-1.5-FlashModel capacity=Frontier (approx. 700B), Input format=Socratic configuration2026.05 | 69 | |
| RECIPE-RL 7BModel configuration=7B2026.05 | 46.1 | |
| Qwen2.5-7B (Base)Model configuration=7B2026.05 | 32.5 |