Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Visual-Language Bundle Quality Assessment on Audited evaluation suite
Loading...
93.1
Semantic Score
AnnotateAnything
76.148
80.549
84.95
89.351
Jun 16, 2026
Semantic Score
3D Grounding Score
Coverage Score
Action Score
Overall Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Semantic Score
3D Grounding Score
Coverage Score
Action Score
Overall Score
AnnotateAnything
Configuration=Full pip...
2026.06
93.1
89.4
90.2
91
90.9
w/o 3D refine
3D Refinement=None
2026.06
87.5
73.4
77.8
75.2
78.5
Direct VLM
2026.06
84.2
61.5
68.7
64.1
69.6
Aff.-only + heur.
Configuration=Affordan...
2026.06
76.8
70.2
73.1
67.5
71.9
Feedback
Search any
task
Search any
task