Procedural Planning on NIV Zero-shot
62.6Macro AccuracyGemini-1.5-Flash
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini-1.5-FlashModel capacity=Frontier (approx. 700B), Input format=Socratic configuration2026.05 | 62.6 | |
| GPT-4o-miniModel capacity=Frontier (approx. 700B), Input format=Socratic configuration2026.05 | 61.6 |