Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Puzzle Solving on Sokoban Hard
Loading...
0.847
Score
Standard PER
0.4986
0.58905
0.6795
0.76995
Apr 18, 2026
Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Score
Standard PER
Type=LLM
2026.04
0.847
On-Policy
Type=LLM
2026.04
0.842
FreshPER
Type=LLM
2026.04
0.512
Feedback
Search any
task
Search any
task
