Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Constrained Text Generation on Natural Language Benchmarks Between (ubd.) constraint
Loading...
93.8
Saturation
DIFFINITY
-3.544
21.728
47
72.272
Feb 12, 2026
Saturation
Pass@10
Perplexity
Fluency
Updated 4d ago
Evaluation Results
Method
Method
Links
Saturation
Pass@10
Perplexity
Fluency
DIFFINITY
Guidance scale=2.5
2026.02
93.8
100
57.4
33.3
GPT2-Large-GCD
Guided Character Decod...
2026.02
3.5
10
71.2
47.1
GPT2-Medium-GCD
Guided Character Decod...
2026.02
0.2
5
132.6
33.3
Feedback
Search any
task
Search any
task