Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Structured Video Reasoning on Maze Overall
Loading...
90.3
Exact Match Percentage
TBS-20
49.428
60.039
70.65
81.261
Jun 11, 2026
Exact Match Percentage
Normalized Time Cost
Updated 1mo ago
Evaluation Results
Method
Method
Links
Exact Match Percentage
Normalized Time Cost
TBS-20
Budget=20
2026.06
90.3
4.42
TBS-10
Budget=10
2026.06
84
3.53
BoN-20
Budget=20
2026.06
79
6.25
BoN-10
Budget=10
2026.06
75.2
4.01
BoN-5
Budget=5
2026.06
67.7
2.58
BoN-1
Budget=1
2026.06
51
1
Feedback
Search any
task
Search any
task
