Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Concept Induction on Bongard-OpenWorld 44 problems
Loading...
91
Binary Accuracy
Human performance
44.824
56.812
68.8
80.788
Jul 1, 2026
Binary Accuracy
Delta vs. Vanilla
Updated 23d ago
Evaluation Results
Method
Method
Links
Binary Accuracy
Delta vs. Vanilla
Human performance
2026.07
91
-
ReVisIT
backbone=GPT-4.1, task...
2026.07
72.7
26.1
GPT-4V (published)
source=original benchm...
2026.07
64
-
GPT-4.1 (vanilla)
backbone=GPT-4.1, few-...
2026.07
46.6
-
Feedback
Search any
task
Search any
task