Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Structured video reasoning on Maze3D Hard
Loading...
95.3
Exact Match
TBS-20
72.108
78.129
84.15
90.171
Jun 11, 2026
Exact Match
Updated 1mo ago
Evaluation Results
Method
Method
Links
Exact Match
TBS-20
Budget=20
2026.06
95.3
TBS-10
Budget=10
2026.06
94.3
BoN-20
Budget=20
2026.06
93.7
BoN-10
Budget=10
2026.06
92.7
BoN-5
Budget=5
2026.06
91
BoN-1
Budget=1
2026.06
73
Feedback
Search any
task
Search any
task
