Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Text Generation on MSC
Loading...
1.23
SacreBLEU
Base Model
1.0116
1.0683
1.125
1.1817
Dec 3, 2025
SacreBLEU
ROUGE-L
BERT-F1
Updated 4d ago
Evaluation Results
Method
Method
Links
SacreBLEU
ROUGE-L
BERT-F1
Base Model
Backbone=Phi-3.5
2025.12
1.23
13.22
74.95
Standard DPO
2025.12
1.21
13.11
74.93
DZ-TDPO
2025.12
1.1
13.03
74.4
SimPO
2025.12
1.07
13.08
74.8
TDPO-DKL
DZ-TA=false
2025.12
1.02
12.92
74.34
Feedback
Search any
task
Search any
task