Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Vision-Language Spatial Reasoning on WhatsUp B-LR 2x2 directional variants
Loading...
82.84
GroupScore
TTM
-3.3136
19.0532
41.42
63.7868
Oct 9, 2025
GroupScore
Absolute Gain (Δ)
Relative Gain
Error Reduction
Updated 1mo ago
Evaluation Results
Method
Method
Links
GroupScore
Absolute Gain (Δ)
Relative Gain
Error Reduction
TTM
Protocol=Algorithm 1
2025.10
82.84
27
48.2
61.1
SimpleMatch
Protocol=GroupMatch
2025.10
55.88
-
-
-
CLIP-B32
Type=Raw performance,...
2025.10
0
-
-
-
Feedback
Search any
task
Search any
task