Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Action, Multi-action, and Trajectory level performance evaluation on MMTB (main)

58.1Overall Performance (All)

EDV

46.45249.47652.555.524Jun 23, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
58.160.9484.3846.0951.5937.529.7639.8350.42
2026.06
55.9659.3879.6944.1448.4118.7529.7635.359.3
2026.06
54.7957.8175.7843.7550.96252538.1753.1
2026.06
53.6756.4783.9839.8442.042520.7332.2240.03
2026.06
52.6155.27541.0247.118.7527.7138.2447.22
2026.06
52.3454.374.2239.4548.41252540.6647.07
2026.06
51.5656.6483.236.7242.0412.59.5229.0529.31
2026.06
49.2257.0368.936.3341.2931.2522.629.6251.09
2026.06
46.956.6469.0531.3741.9418.7511.914.2241.21