List your company

Embodied Manipulation on EB-Manipulation

42Average ScoreClaude-3.7
13.9221.2128.535.79May 26, 2026

Evaluation results

MethodLinks
Claude-3.7Tool use=Yes2026.05424644503633
Claude-3.7Tool use=No2026.05383338463338
Claude-4.6Tool use=Yes2026.05384035424031
GPT-4oTool use=Yes2026.05374431403635
Claude-4.6Tool use=No2026.05374035403637
GPT-5Tool use=Yes2026.05354227443131
GPT-4oTool use=No2026.05313129273633
Qwen2.5-32BTool use=Yes2026.05292735332128
GPT-5Tool use=No2026.05272125312235
Qwen3-8BTool use=Yes2026.05272935311919
Qwen3.5-35BTool use=Yes2026.05273329272223
Qwen3-32BTool use=Yes2026.05252725311722
Qwen3-32BTool use=No2026.05202125171919
Qwen3-8BTool use=No2026.0519151525631
Qwen2.5-32BTool use=No2026.05171313231125
Qwen3.5-35BTool use=No2026.05151317151717