Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Structured video reasoning on Sliding Puzzle Med.
Loading...
89
Success Rate
TBS-20
43.24
55.12
67
78.88
Jun 11, 2026
Success Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate
TBS-20
Budget=20
2026.06
89
TBS-10
Budget=10
2026.06
86
BoN-20
Budget=20
2026.06
86
BoN-10
Budget=10
2026.06
80.5
BoN-5
Budget=5
2026.06
75.5
BoN-1
Budget=1
2026.06
45
Feedback
Search any
task
Search any
task