Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multimodal Content Generation on Human Evaluation N=20 (test)
Loading...
19
Win Count
CogGen
9.64
12.07
14.5
16.93
Apr 18, 2026
Win Count
Overall Quality
Visual-Text Alignment
Multimodal Synergy
Content Depth
Tie Count
Loss Count
Win Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Win Count
Overall Quality
Visual-Text Alignment
Multimodal Synergy
Content Depth
Tie Count
Loss Count
Win Rate
CogGen
Dimension=Content Dept...
2026.04
19
-
-
-
-
0
1
95
CogGen
Dimension=Overall Qual...
2026.04
18
-
-
-
-
1
1
90
CogGen
Comparison Baseline=Ge...
2026.04
16
-
80
-
-
0
4
80
CogGen
Comparison Baseline=Ge...
2026.04
16
-
-
80
-
1
3
80
CogGen
Dimension=Visual-Text...
2026.04
16
-
-
-
-
2
2
80
CogGen
Dimension=Multimodal S...
2026.04
16
-
-
-
-
2
2
80
CogGen
Comparison Baseline=Ge...
2026.04
15
75
-
-
-
1
4
75
CogGen
Comparison Baseline=Ge...
2026.04
10
-
-
-
50
3
7
50
Feedback
Search any
task
Search any
task
