Action Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.146MMD (Average)
16
Feb 26, 2026
0.342METEOR
13
Feb 26, 2026
0.031Latency (s)
10
Jun 9, 2026
89DINO-R
6
Feb 26, 2026
0.005Safety Violation Rate
5
Jun 12, 2026
100Safety
5
Jun 12, 2026
72.6Success Rate
5
Feb 26, 2026
32.4Rule-based Score
4
Jun 30, 2026
31.2Rule-based
4
Jun 30, 2026
36.6Rule-based Score
4
Jun 30, 2026
70Spatial Success Rate
3
Apr 13, 2026
0.407Inference Time (ms)
3
Feb 26, 2026
58.3Preference Rate
3
Feb 26, 2026
4.82Overall Score
3
Feb 26, 2026