Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Exploration on ARC-AGI-3
Loading...
4
TU93 Level
MAP
-0.16
0.92
2
3.08
May 13, 2026
TU93 Level
TU93 Score
SB26 Level
SB26 Score
VC33 Level
VC33 Score
RE86 Level
RE86 Score
AR25 Level
AR25 Score
WA30 Level
WA30 Score
Updated 20d ago
Evaluation Results
Method
Method
Links
TU93 Level
TU93 Score
SB26 Level
SB26 Score
VC33 Level
VC33 Score
RE86 Level
RE86 Score
AR25 Level
AR25 Score
WA30 Level
WA30 Score
MAP
Backbone=Claude 4.6 Opus
2026.05
4
3.34
3
7.59
3
4.12
3
11.59
3
7.66
2
6.67
ReAct
Backbone=Claude 4.6 Opus
2026.05
0
0
1
0.19
0
0
0
0
0
0
0
0
Feedback
Search any
task
Search any
task