List your company

Task Planning on EB-ALFRED (Long)

74Success Rate (SR)BrainMem
-2.9617.023756.98Aug 2, 2025Sep 8, 2025Oct 15, 2025Nov 21, 2025Dec 28, 2025Feb 3, 2026Mar 12, 2026

Evaluation results

MethodLinks
BrainMemEvaluation Model=Qwen2.5-VL-72B-Ins2026.037482.6
Claude-3.7-SonnetType=Closed-source2025.0870—
RoboMemoryType=Ours, Backbone=Qwen2.5-VL-72B-Ins2025.086681.3
RoboMemoryEvaluation Model=Qwen2.5-VL-72B-Ins2026.036681.3
Gemini-1.5-ProType=Closed-source2025.085865
Gemini-2.0-flashType=Closed-source2025.085862
GPT-4oType=Closed-source2025.085462.5
Claude-3.5-SonnetType=Closed-source2025.085254.5
InternVL2.5-78BType=Open-source2025.084249
InternVL3-78BType=Open-source2025.0836—
Qwen2.5-VL-72B-InsType=Open-source2025.0834—
VoyagerType=Baselines, Backbone=Qwen2.5-VL-72B-Ins2025.083254.2
CradleType=Baselines, Backbone=Qwen2.5-VL-72B-Ins2025.083241
VoyagerEvaluation Model=Qwen2.5-VL-72B-Ins2026.033254.2
CradleEvaluation Model=Qwen2.5-VL-72B-Ins2026.033241
InternVL2.5-38BType=Open-source2025.082636.5
Llama-3.2-90B-Vision-InsType=Open-source2025.081624
RoboOSType=Baselines, Backbone=Qwen2.5-VL-72B-Ins2025.081217.6
RoboOSEvaluation Model=Qwen2.5-VL-72B-Ins2026.031217.6
ReflexionType=Baselines, Backbone=Qwen2.5-VL-72B-Ins2025.081033
ReflexionEvaluation Model=Qwen2.5-VL-72B-Ins2026.031033
RoboOSType=Baselines, Backbone=RoboBrain2-32B2025.08813.2
GPT-4o-miniType=Closed-source2025.08017