List your company

Game strategy reasoning on IsoBench Game

64.6Winner IDGPT-4o + Sketchpad
5.11220.5563651.444Jun 13, 2024

Evaluation results

MethodLinks
GPT-4o + SketchpadVisual Input=true, Sketchpad=true2024.0664.6
GPT-4 Turbo + SketchpadVisual Input=true, Sketchpad=true2024.0664.2
GPT-4oVisual Input=true, Sketchpad=false2024.0661.1
GPT-4 TurboVisual Input=true, Sketchpad=false2024.0650.4
LLaMA-2-70BVisual Input=false2024.0612.4
Gemini-ProVisual Input=false2024.068.1
Mixtral 8x7BVisual Input=false2024.067.4