List your company

Instruction Following on ALFRED seen (test)

29.16Task Success RateOurs (multiple views)
2.83769.671316.50523.3387May 20, 2026

Evaluation results

MethodLinks
Ours (multiple views)View Configuration=multiple views2026.0529.1624.6738.8234.85
MOCA2026.0522.0515.128.2922.05
Ours (single view)View Configuration=single view2026.0515.211.7923.9520.27
Ours (winning entry)View Configuration=winning entry2026.0512.398.220.6818.79
Singh et al.2026.055.412.5112.328.27
Shridhar et al.2026.053.982.029.426.27
Legg et al.2026.053.851.58.875.52