Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Code Generation on CodeAlpaca (Score)
Loading...
33.2
Score
EPI
-0.62496
8.15652
16.938
25.71948
Apr 15, 2026
Apr 21, 2026
Apr 27, 2026
May 3, 2026
May 9, 2026
May 15, 2026
May 21, 2026
Score
Updated 12d ago
Evaluation Results
Method
Method
Links
Score
EPI
Base Model=Gemma-2-9B,...
2026.04
33.2
Static Isolation
Base Model=Gemma-2-9B,...
2026.04
31.5
EPI
Base Model=LLaMA-3-8B,...
2026.04
31.2
Full SFT
Base Model=Gemma-2-9B,...
2026.04
30.1
Static Isolation
Base Model=LLaMA-3-8B,...
2026.04
29.4
Full SFT
Base Model=LLaMA-3-8B,...
2026.04
28.3
Base model
Backbone=Qwen2.5-0.5B-...
2026.05
0.683
SPD-QA
Backbone=Qwen2.5-0.5B-...
2026.05
0.68
SSD-QA
Backbone=Qwen2.5-0.5B-...
2026.05
0.676
Feedback
Search any
task
Search any
task