Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long-horizon Reasoning on Checkers Jumping (n=13 to n=16)
Loading...
100
Performance (n=13)
Lookahead-Enhanced Atomic Decomposition
-4
23
50
77
Mar 6, 2026
Performance (n=13)
Performance (n=14)
Performance (n=15)
Performance (n=16)
Updated 4mo ago
Evaluation Results
Method
Method
Links
Performance (n=13)
Performance (n=14)
Performance (n=15)
Performance (n=16)
Lookahead-Enhanced Atomic Decomposition
Model=GPT-5.2, Voting=...
2026.03
100
100
87
100
Atomic Decomposition
Model=GPT-5.2, Voting=...
2026.03
20
100
0
96
Atomic Decomposition
Model=GPT-5.2, Voting=...
2026.03
0
36
0
4
Feedback
Search any
task
Search any
task