List your company

Step Completion on CoSPlan Maze-E

46.1AccuracyGPT-4o
18.95626.00333.0540.097Dec 11, 2025

Evaluation results

MethodLinks
GPT-4oReasoning Strategy=Scene Graph2025.1246.1
GPT-4oReasoning Strategy=Chain-of-Thought2025.1245.6
Intern-VLMReasoning Strategy=Scene Graph2025.1241.2
Intern-VLMReasoning Strategy=Chain-of-Thought2025.1235.8
Qwen2 VL-8BReasoning Strategy=Scene Graph2025.1228.3
Qwen2 VL-8BReasoning Strategy=Chain-of-Thought2025.1227.9
Qwen2 VL-8BReasoning Strategy=Vanilla2025.1226.5
CoG-VLMReasoning Strategy=Scene Graph2025.1226.5
CoG-VLMReasoning Strategy=Chain-of-Thought2025.1225.9
CoG-VLMReasoning Strategy=Vanilla2025.1225.1
Janus-pro-7BReasoning Strategy=Scene Graph2025.1221.7
Intern-VLMReasoning Strategy=Vanilla2025.1221.6
Janus-pro-7BReasoning Strategy=Vanilla2025.1220.4
Janus-pro-7BReasoning Strategy=Chain-of-Thought2025.1220.2
Random2025.1220