HumanEvalFix(Python)
2 models
Top 5 Models Performance
| IBM Granite: Granite-34B-Code-Instruct-8K | ######################################## | 54.9 |
| IBM Granite: Granite-20B-Code-Instruct-8K | ################################ | 43.9 |
| Rank | Model | Score | |
|---|---|---|---|
| 🇺🇸 | 1 | IBM Granite: Granite-34B-Code-Instruct-8K | 54.9 |
| 🇺🇸 | 2 | IBM Granite: Granite-20B-Code-Instruct-8K | 43.9 |