Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Structured Video Reasoning on Maze Easy
Loading...
100
Exact Match Accuracy
BoN-5
97.92
98.46
99
99.54
Jun 11, 2026
Exact Match Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Exact Match Accuracy
BoN-5
Budget=5
2026.06
100
BoN-10
Budget=10
2026.06
100
TBS-10
Budget=10
2026.06
100
BoN-20
Budget=20
2026.06
100
TBS-20
Budget=20
2026.06
100
BoN-1
Budget=1
2026.06
98
Feedback
Search any
task
Search any
task
