Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Structured video reasoning on Keys and Doors Overall
Loading...
99.2
Exact Match Percentage
TBS-20
50.424
63.087
75.75
88.413
Jun 11, 2026
Exact Match Percentage
Time (ID)
Time (OOD)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Exact Match Percentage
Time (ID)
Time (OOD)
TBS-20
Budget=20
2026.06
99.2
2.6
18.13
BoN-20
Budget=20
2026.06
97.7
2.86
19.66
TBS-10
Budget=10
2026.06
96.5
2.59
9.31
BoN-10
Budget=10
2026.06
94.5
2.51
9.89
BoN-5
Budget=5
2026.06
89.2
2.1
4.95
BoN-1
Budget=1
2026.06
52.3
1
1
Feedback
Search any
task
Search any
task
