Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Human Fluency Evaluation on HUMANITY
Loading...
9.1
Generation Score
SGM
6.812
7.406
8
8.594
Dec 17, 2025
Generation Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Generation Score
SGM
Backbone=ShareGPT4V-13B
2025.12
9.1
BASE
Backbone=ShareGPT4V-13B
2025.12
8.8
ECSO
Backbone=ShareGPT4V-7B
2025.12
8.3
ECSO
Backbone=ShareGPT4V-13B
2025.12
8.2
ECSO
Backbone=LLaVA-1.5-13B
2025.12
8
BASE
Backbone=ShareGPT4V-7B
2025.12
7.9
SGM
Backbone=ShareGPT4V-7B
2025.12
7.9
SGM
Backbone=LLaVA-1.5-13B
2025.12
7.7
BASE
Backbone=LLaVA-1.5-13B
2025.12
7.5
BASE
Backbone=LLaVA-1.5-7B
2025.12
7.2
ECSO
Backbone=LLaVA-1.5-7B
2025.12
7.1
SGM
Backbone=LLaVA-1.5-7B
2025.12
6.9
Feedback
Search any
task
Search any
task