Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Open-ended Generation on Human Evaluation Scores
Loading...
4.4
Quality Score
STA
3.256
3.553
3.85
4.147
Feb 4, 2026
Quality Score
Alignment Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Quality Score
Alignment Score
STA
Backbone=Gemma2-9B-it
2026.02
4.4
4.7
AUSteer
Backbone=Gemma2-9B-it
2026.02
4.3
4.7
AUSteer
Backbone=Qwen3-8B
2026.02
4.3
4.1
SADI
Backbone=Gemma2-9B-it
2026.02
4.2
4.5
SADI
Backbone=Qwen3-8B
2026.02
4.1
3.9
AUSteer
Backbone=LLaMA2-7B-Chat
2026.02
3.4
3.8
SADI
Backbone=LLaMA2-7B-Chat
2026.02
3.3
3.6
Feedback
Search any
task
Search any
task