List your company

Step Completion on CoSPlan Robo-VQA-E

52.2AccuracyGPT-4o
10.91221.63132.3543.069Dec 11, 2025

Evaluation results

MethodLinks
GPT-4oReasoning Strategy=Scene Graph2025.1252.2
GPT-4oReasoning Strategy=Chain-of-Thought2025.1248.2
Intern-VLMReasoning Strategy=Scene Graph2025.1225.1
Intern-VLMReasoning Strategy=Chain-of-Thought2025.1223.5
Intern-VLMReasoning Strategy=Vanilla2025.1222.1
CoG-VLMReasoning Strategy=Scene Graph2025.1221.5
Janus-pro-7BReasoning Strategy=Scene Graph2025.1221.3
Random2025.1220
Qwen2 VL-8BReasoning Strategy=Scene Graph2025.1218.9
Qwen2 VL-8BReasoning Strategy=Chain-of-Thought2025.1217.6
Qwen2 VL-8BReasoning Strategy=Vanilla2025.1217.1
Janus-pro-7BReasoning Strategy=Chain-of-Thought2025.1214.7
Janus-pro-7BReasoning Strategy=Vanilla2025.1214.1
CoG-VLMReasoning Strategy=Vanilla2025.1213.1
CoG-VLMReasoning Strategy=Chain-of-Thought2025.1212.5