List your company

Task Planning on EB-Habitat Long

64Success Rate (SR)GPT-4o
9.9223.963852.04Aug 2, 2025Sep 8, 2025Oct 15, 2025Nov 21, 2025Dec 28, 2025Feb 3, 2026Mar 12, 2026

Evaluation results

MethodLinks
GPT-4oType=Closed-source2025.086472.2
RoboMemoryType=Ours, Backbone=Qwen2.5-VL-72B-Ins2025.086274
RoboMemoryEvaluation Model=Qwen2.5-VL-72B-Ins2026.036274
BrainMemEvaluation Model=Qwen2.5-VL-72B-Ins2026.036275.3
Claude-3.5-SonnetType=Closed-source2025.085863.3
Gemini-1.5-ProType=Closed-source2025.085261.2
Claude-3.7-SonnetType=Closed-source2025.0846—
InternVL3-78BType=Open-source2025.0840—
CradleType=Baselines, Backbone=Qwen2.5-VL-72B-Ins2025.083052.1
CradleEvaluation Model=Qwen2.5-VL-72B-Ins2026.033052.1
InternVL2.5-78BType=Open-source2025.082838.2
InternVL2.5-38BType=Open-source2025.082835
Gemini-2.0-flashType=Closed-source2025.082636.2
VoyagerType=Baselines, Backbone=Qwen2.5-VL-72B-Ins2025.082251
VoyagerEvaluation Model=Qwen2.5-VL-72B-Ins2026.032251
RoboOSType=Baselines, Backbone=Qwen2.5-VL-72B-Ins2025.082028.2
RoboOSEvaluation Model=Qwen2.5-VL-72B-Ins2026.032028.2
Qwen2.5-VL-72B-InsType=Open-source2025.0818—
ReflexionType=Baselines, Backbone=Qwen2.5-VL-72B-Ins2025.081533
ReflexionEvaluation Model=Qwen2.5-VL-72B-Ins2026.031533
GPT-4o-miniType=Closed-source2025.081421.3
Llama-3.2-90B-Vision-InsType=Open-source2025.081424.3
RoboOSType=Baselines, Backbone=RoboBrain2-32B2025.081217.4