This is the repo for our TMLR survey Unifying the Perspectives of NLP and Software Engineering: A Survey on Language Models for Code - a comprehensive review of LLM researches for code. Works in each category are ordered chronologically.

Nov 8, 2024 · Measuring the LLM’s coding ability, and whether it can write new code that integrates into existing code. BigCodeBench evaluates LLMs with practical and challenging programming tasks. Holistic and Contamination Free Evaluation of …

Dec 20, 2024 · In this blog, we’ll explore some of the best LLMs for coding and developers, including Llama 3.3, Claude 3.5 Sonnet, GPT-O1, Qwen Qwq, Mistral, Gemini Flash 2.0, and Gemini Exp 1206. Each model has unique strengths and trade-offs, so we’ll help you decide based on your specific needs.

May 4, 2023 · StarCoder and StarCoderBase are Large Language Models for Code (Code LLMs) trained on permissively licensed data from GitHub, including from 80+ programming languages, Git commits, GitHub issues, and Jupyter notebooks. Similar to LLaMA, we trained a ~15B parameter model for 1 trillion tokens.

Jun 1, 2024 · Large Language Models (LLMs) have garnered remarkable advancements across diverse code-related tasks, known as Code LLMs, particularly in code generation that generates source code with LLM from natural language descriptions.

Aug 24, 2023 · Code Llama is state-of-the-art for publicly available LLMs on code tasks, and has the potential to make workflows faster and more efficient for current developers and lower the barrier to entry for people who are learning to code.

Feb 11, 2025 · Among all the stability models, the best coding LLM is Stable Code 3B. In particular, it stands out for its ability to perform FIM (Fill-in-the-Middle) tasks. This ability allows this model to generate code that fills in a missing section in the middle of an existing code snippet. This is different from traditional code completion, which ...

Nov 19, 2024 · OpenCoder is an open and reproducible code LLM family which includes 1.5B and 8B base and chat models, supporting both English and Chinese languages.

Mar 7, 2025 · For instance, writing code in a syntax-heavy language like Python, Java, or C++ suggests using an LLM that specializes in real-time suggestions and syntax corrections. Working with a complex tech stack means you may want to prioritize LLMs that support multiple programming languages and offer features like code generation, debugging, and ...

OpenCoder is an open and reproducible code LLM family which includes 1.5B and 8B base and chat models, supporting both English and Chinese languages. Starting from scratch, OpenCoder is trained on 2.5 trillion tokens composed of 90% raw code and 10% code-related web data, reaching the performance of top-tier code LLMs.