Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Structured video reasoning on Sokoban Hard
Loading...
79.7
Exact Match
TBS-20
35.292
46.821
58.35
69.879
Jun 11, 2026
Exact Match
Updated 1mo ago
Evaluation Results
Method
Method
Links
Exact Match
TBS-20
Budget=20
2026.06
79.7
BoN-20
Budget=20
2026.06
78.3
TBS-10
Budget=10
2026.06
73
BoN-10
Budget=10
2026.06
72.3
BoN-5
Budget=5
2026.06
63.3
BoN-1
Budget=1
2026.06
37
Feedback
Search any
task
Search any
task
