Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Structured video reasoning on Sokoban Med.
Loading...
79.5
Exact Match (%)
BoN-20
28.02
41.385
54.75
68.115
Jun 11, 2026
Exact Match (%)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Exact Match (%)
BoN-20
Budget=20
2026.06
79.5
TBS-20
Budget=20
2026.06
79
TBS-10
Budget=10
2026.06
74.5
BoN-10
Budget=10
2026.06
70
BoN-5
Budget=5
2026.06
59.5
BoN-1
Budget=1
2026.06
30
Feedback
Search any
task
Search any
task
