Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Visual Puzzle Solving on VisPuzzle
Loading...
86
Accuracy
Visual-OPSD
28.28
43.265
58.25
73.235
Jun 17, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Visual-OPSD
3-run average=true, La...
2026.06
86
GPT-5
3-run average=true
2026.06
78
ThinkMorph
3-run average=true, La...
2026.06
77.5
Visual-OPSD-Noise
3-run average=true, La...
2026.06
64.5
Text-only SFT
3-run average=true, La...
2026.06
63.5
Qwen3-VL-32B
3-run average=true
2026.06
50.75
GPT-4o
3-run average=true
2026.06
43.75
Qwen3-VL-8B
3-run average=true
2026.06
37
InternVL3.5-38B
3-run average=true
2026.06
36.5
BAGEL-7B
3-run average=true
2026.06
35
InternVL3.5-8B
3-run average=true
2026.06
34.75
Janus-Pro-7B
3-run average=true
2026.06
33.5
Chameleon-7B
3-run average=true
2026.06
30.5
Feedback
Search any
task
Search any
task