Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Utility Evaluation on MMbench and DocVQA (test)
Loading...
87.02
MMbench Score
Full Model
83.7544
84.6022
85.45
86.2978
May 22, 2025
MMbench Score
DocVQA Score
Average Utility Score
Updated 4d ago
Evaluation Results
Method
Method
Links
MMbench Score
DocVQA Score
Average Utility Score
Full Model
Backbone=Qwen2.5-VL, S...
2025.05
87.02
94.51
90.76
Wanda
Backbone=Qwen2.5-VL, S...
2025.05
85.15
91.97
88.56
Wanda w/ HSR
Backbone=Qwen2.5-VL, S...
2025.05
85.01
92.13
88.57
SNIP w/ HSR
Backbone=Qwen2.5-VL, S...
2025.05
84.62
92.9
88.76
SNIP
Backbone=Qwen2.5-VL, S...
2025.05
84.55
92.93
88.74
SparseGPT
Backbone=Qwen2.5-VL, S...
2025.05
83.88
90.64
87.26
SparseGPT w/ HSR
Backbone=Qwen2.5-VL, S...
2025.05
83.88
90.63
87.25
Feedback
Search any
task
Search any
task