List your company

Embodied Instruction Following on EB-ALFRED 1.0 (test)

67.2Success Rate (Avg)ReAct
27.26437.6324858.368Jan 19, 2026

Evaluation results

MethodLinks
ReActBackbone=Claude-3.7-Sonnet2026.0167.2686870686265.3726676.76359.7
ReActBackbone=Gemini-1.5-Pro2026.0163.2706472585267.474.366.776.562.859
ReActBackbone=GPT-4o2026.0156.8645468465265.17460.37458.361.3
WorldMindBackbone=GPT-4.1-mini2026.0149.2505854424255.7616158.84849.7
WorldMindBackbone=GPT-3.5-turbo2026.0148584856344454.16352.76141.752
SimuRABackbone=GPT-4.1-mini2026.0145.6524454384052.26150.358.245.346.3
SimuRABackbone=GPT-3.5-turbo2026.0145.2504254384253.657.847.859.748.554.3
ReActBackbone=GPT-3.5-turbo2026.0144.4524852323850.455.353.555.342.745
BoNBackbone=GPT-4.1-mini2026.0144.4464450424049.550.848.354.748.745
BoNBackbone=GPT-3.5-turbo2026.0142.8464250423450.454.246.556.55242.8
ReasoningBankBackbone=GPT-3.5-turbo2026.0141.6503644364247.657.541.54744.248
ReActBackbone=GPT-4.1-mini2026.0141.2504046383247.555.342.852.247.239.8
AWMBackbone=GPT-4.1-mini2026.0141.244364838404648.34252.544.342.7
AWMBackbone=GPT-3.5-turbo2026.0140463248403446.253.239.250.74741
SynapseBackbone=GPT-3.5-turbo2026.0138.8384640363443.642.551.342.74239.7
ReasoningBankBackbone=GPT-4.1-mini2026.0138423642343642.646.738.845.841.540.3
SynapseBackbone=GPT-4.1-mini2026.0137.2403244363442.241.237.549.541.341.7
ReActBackbone=InternVL2.5-78B2026.013741403916494142.335.343.335.740.3
ReActBackbone=Llama-3.2-90B-Vis2026.0135.2383444283237.643.737.349.235.336
ReActBackbone=GPT-4o-mini2026.0128.8342836242234.347.835.343.533.329