Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Visual Puzzles on VPCT
Loading...
90
Pass@1
Gemini-3-Pro High
26.56
43.03
59.5
75.97
Jun 30, 2026
Pass@1
Updated 24d ago
Evaluation Results
Method
Method
Links
Pass@1
Gemini-3-Pro High
2026.06
90
Seed2.0 Pro
2026.06
76
Seed2.0 Lite
2026.06
73
Seed1.8
2026.06
61
GPT-5.2 High
2026.06
56
Seed2.0 Mini
2026.06
48
Claude-Opus-4.5
2026.06
29
Feedback
Search any
task
Search any
task