HumanEval
HumanEval - Python code generation from function signatures and docstrings. 0-shot.
Category
Code
Max Score
100.0
Score Type
percent
Active
Yes
Model Scores
Scores for HumanEval
| Model | Score | Date | Verified |
|---|---|---|---|
| Gemma 3 4B PT |
36.00
|
27.02.2025 | Verified |
| Gemma 3 12B PT |
75.78%
|
27.02.2025 | Verified |
| Gemma 3 27B PT |
100.00%
|
27.02.2025 | Verified |