List your company

Embodied Planning on EB-Habitat (unseen)

57Avg Success RateGPT-4o
-2.2813.1128.543.89Oct 16, 2025

Evaluation results

MethodLinks
GPT-4oType=Closed-Source General Model, Params=-2025.1057844262386254
GPT-4.1Type=Closed-Source General Model, Params=-2025.1050.67903850364644
Qwen2.5-VL-72B-InsType=Open-Source General Model, Params=72B2025.1050.33923848344644
Qwen-VL-MaxType=Closed-Source General Model, Params=-2025.1045.3744050423036
Gemini-2.0-flashType=Closed-Source General Model, Params=-2025.1042.3823838363426
Llama-3.2-90B-Vision-InsType=Open-Source General Model, Params=90B2025.1040.3942450322814
GPT-4o-miniType=Closed-Source General Model, Params=-2025.1035702436303020
Gemma-3-12b-itsType=Open-Source General Model, Params=12B2025.102358102418244
RoboGPT-R1Type=Embodied Planning Model, Params=3B2025.102264818201210
REBPType=Embodied Planning Model, Params=7B2025.1018.335061814148
RoboBrainType=Embodied Planning Model, Params=7B2025.1015.3386188184
Qwen2.5-VL-7B-InsType=Open-Source General Model, Params=7B2025.1015426221244
Qwen2.5-VL-3B-InsType=Open-Source General Model, Params=3B2025.1014.673401818144
InternVL2.5-8BType=Open-Source General Model, Params=8B2025.1011.3364010162
TapaType=Embodied Planning Model, Params=7B2025.100000000