deepseek-ai / DeepSeek-Coder-V2

DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

paper number not aligned

lwaekfjlk opened this issue · comments

In the first figure, gemini-1.5-pro on swe-bench is 18.3% while in the table it is 19.7%