Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Code Generation on Unseen simple code generation tasks (test)
Loading...
0.29
Loss
FiFSL
0.288
0.3015
0.315
0.3285
Dec 5, 2025
Loss
Pass@1
BLEU
chrF
Updated 1mo ago
Evaluation Results
Method
Method
Links
Loss
Pass@1
BLEU
chrF
FiFSL
Model=DeepSeek-7B, For...
2025.12
0.29
79
36.7
59.3
FiFSL
Model=Llama-8B, Forget...
2025.12
0.33
73
44.2
62.4
FiFSL
Model=Llama-7B, Forget...
2025.12
0.34
73
46
67
Feedback
Search any
task
Search any
task
