deepseek-ai/DeepSeek-Coder
DeepSeek Coder: Let the Code Write Itself
We introduced a new model designed for the Code generation task. Its test accuracy on the HumanEval base dataset surpasses that of GPT-4 Turbo (April 2024) and GPT-4o.
DeepSeek Coder: Let the Code Write Itself
The Open Cookbook for Top-Tier Code Large Language Model
Rigourous evaluation of LLM-synthesized code - NeurIPS 2023 & COLM 2024
A natural language interface for computers
[ICLR'25] BigCodeBench: Benchmarking Code Generation Towards AGI
Xcode Source Editor Extension with OpenAI's API
1 capture since 2026-05-27