Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multimodal Mathematical Reasoning on WeMath
Loading...
36.33
WeMath-S Score
GAP (LH+PCA+DA)
26.5748
29.1074
31.64
34.1726
May 12, 2026
WeMath-S Score
WeMath-L Score
Average Reasoning Score
Updated 21d ago
Evaluation Results
Method
Method
Links
WeMath-S Score
WeMath-L Score
Average Reasoning Score
GAP (LH+PCA+DA)
Latent Head (LH)=true,...
2026.05
36.33
54.57
53.97
Qwen2.5-VL 7B
Parameters=7B
2026.05
36.29
53.06
52.62
GAP (LH+PCA)
Latent Head (LH)=true,...
2026.05
35.24
52
52.48
Monet-7B
Parameters=7B
2026.05
32.67
50
47.99
GAP (LH+DA, no PCA)
Latent Head (LH)=true,...
2026.05
31.26
50
50.05
GAP (LH)
Latent Head (LH)=true
2026.05
30
48.86
49.15
Dense Cap SFT
2026.05
28.6
45.43
47.24
LVR
2026.05
26.95
49.05
47.66
Feedback
Search any
task
Search any
task