Game strategy reasoning on IsoBench Game
64.6Winner IDGPT-4o + Sketchpad
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-4o + SketchpadVisual Input=true, Sketchpad=true2024.06 | 64.6 | |
| GPT-4 Turbo + SketchpadVisual Input=true, Sketchpad=true2024.06 | 64.2 | |
| GPT-4oVisual Input=true, Sketchpad=false2024.06 | 61.1 | |
| GPT-4 TurboVisual Input=true, Sketchpad=false2024.06 | 50.4 | |
| LLaMA-2-70BVisual Input=false2024.06 | 12.4 | |
| Gemini-ProVisual Input=false2024.06 | 8.1 | |
| Mixtral 8x7BVisual Input=false2024.06 | 7.4 |