Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Veracity-focused Explanation Generation on Hindi News Human Evaluation (test)
Loading...
4.23
Human Evaluation Score
Hin-DPO
3.0236
3.3368
3.65
3.9632
Jul 7, 2025
Human Evaluation Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Human Evaluation Score
Hin-DPO
Backbone=Llama3.1-8B
2025.07
4.23
Hin-DPO
Backbone=Gemma2-9B
2025.07
4.12
DPO
Backbone=Gemma2-9B
2025.07
3.92
DPO
Backbone=Llama3.1-8B
2025.07
3.87
Base+SFT
Backbone=Gemma2-9B
2025.07
3.29
Base+SFT
Backbone=Llama3.1-8B
2025.07
3.07
Feedback
Search any
task
Search any
task