Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Visual Reasoning on Blind (test)
Loading...
90.5
Line Intersections Accuracy (Test)
SEVEX
31.012
46.456
61.9
77.344
Mar 17, 2026
Line Intersections Accuracy (Test)
Circled Letter Accuracy (Test)
Subway Map Accuracy (Test)
Overlapping Shapes Accuracy (Test)
Average Accuracy (Test)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Line Intersections Accuracy (Test)
Circled Letter Accuracy (Test)
Subway Map Accuracy (Test)
Overlapping Shapes Accuracy (Test)
Average Accuracy (Test)
SEVEX
inf. cost (Average-Bli...
2026.03
90.5
83.7
62.8
52.4
72.4
Naive
inf. cost (Average-Bli...
2026.03
73
78.8
60
50.4
65.6
SketchPad
inf. cost (Average-Bli...
2026.03
33.3
82
58.1
16.3
47.4
Feedback
Search any
task
Search any
task
