List your company

Embodied AI Behavior Modeling on Embodied Agent Interface Behavior task

74.9Performanceo1-preview
49.4256.03562.6569.265Apr 23, 2026

Evaluation results

MethodLinks
o1-preview2026.0474.981.68191576270.8
ReCAPA2026.0472.284.87784536069.8
Claude-4-Sonnet2026.0468.584.36875475269.2
Claude-3.5-Sonnet2026.0464.282.76069394467.9
Claude-3-Opus2026.0460.4775159414763.4
GPT-4o2026.0459.879.24753495560.9
o1-mini2026.0457.576.45665313956.4
Claude-3-Sonnet2026.0455.169.44457394356.2
Gemini-1.5-Flash2026.0452.174.84052344253.4
Mistral-Large2026.0450.474.33350313849.5