Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
RTL Code Generation on Syntax-preserving dataset (val)
Loading...
0.28
Loss
FiFSL
0.2776
0.2938
0.31
0.3262
Dec 5, 2025
Loss
Pass@1
BLEU
chrF
Updated 4d ago
Evaluation Results
Method
Method
Links
Loss
Pass@1
BLEU
chrF
FiFSL
Model=DeepSeek-7B, For...
2025.12
0.28
55
49.6
58.3
Llama-7B Base
Model=Llama-7B
2025.12
0.3
49
50.7
59.1
FiFSL
Model=Llama-7B, Forget...
2025.12
0.3
47
50.6
57.9
FiFSL
Model=Llama-8B, Forget...
2025.12
0.31
50
47
55.6
FiFSL
Model=Llama-7B, Forget...
2025.12
0.32
44
49.7
56.8
FiFSL
Model=Llama-7B, Forget...
2025.12
0.33
45
48.8
56.4
FiFSL
Model=Llama-8B, Forget...
2025.12
0.34
49
44
51.8
Feedback
Search any
task
Search any
task
