- 🧵 Table of Contents
- 🚀 Leaderboard
- 💡 Evaluation Toolkit:
- 📚 Paper
- 🙌 Contributors
- Cite as
- Acknowledgement
- Star History
Central Leaderboard (Sort by HumanEval Pass@1)
Model | Params | HumanEval | MBPP | HF | Source |
---|---|---|---|---|---|
GPT-4 + Reflexion | ? | 91.0 | 77.1 | paper | |
GPT-4 (latest) | ? | 84.1 | 80.0 | github | |
CodeQwen1.5-7B-Chat | 7B | 83.5 | 70.6 | ckpt | github |
DeepSeek-Coder-Instruct | 33B | 79.3 | 70.0 | ckpt | github |
DeepSeek-Coder-Instruct | 7B | 78.6 | 65.4 | ckpt | github |
GPT-3.5-Turbo (latest) | ? | 76.2 | 70.8 | github | |
Code-Llama | 34B | 62.2 | 61.2 | paper | |
Pangu-Coder2 | 15B | 61.6 | paper | ||
WizardCoder-15B | 15B | 57.3 | 51.8 | ckpt | paper |
CodeQwen1.5-7B | 7B | 51.8 | 61.8 | ckpt | github |
Code-Davinci-002 | ? | 47.0 | paper | ||
StarCoder-15B (Prompted) | 15B | 40.8 | 49.5 | ckpt | paper |
PaLM 2-S | ? | 37.6 | 50.0 | paper | |
PaLM-Coder-540B | 540B | 36.0 | 47.0 | paper | |
InstructCodeT5+ | 16B | 35.0 | paper | ||
StarCoder-15B | 15B | 33.6 | 52.7 | ckpt | paper |
Code-Cushman-001 | ? | 33.5 | 45.9 | paper | |
CodeT5+ | 16B | 30.9 | paper | ||
LLaMA2-70B | 70B | 29.9 | ckpt | paper | |
CodeGen-16B-Mono | 16B | 29.3 | 35.3 | paper | |
PaLM-540B | 540B | 26.2 | 36.8 | paper | |
LLaMA-65B | 65B | 23.7 | 37.7 | paper | |
CodeGeeX | 13B | 22.9 | 24.4 | paper | |
LLaMA-33B | 33B | 21.7 | 30.2 | paper | |
CodeGen-16B-Multi | 16B | 18.3 | 20.9 | paper | |
AlphaCode | 1.1B | 17.1 | paper |
Leaderboard | Access |
---|---|
Big Code Models Leaderboard | [Source] |
BIRD | [Source] |
CanAiCode Leaderboard | [Source] |
Coding LLMs Leaderboard | [Source] |
CRUXEval Leaderboard | [Source] |
EvalPlus | [Source] |
HumanEval.jl | [Source] |
InfiCoder-Eval | [Source] |
InterCode | [Source] |
Program Synthesis Models Leaderboard | [Source] |
Spider | [Source] |
- bigcode-evaluation-harness: A framework for the evaluation of autoregressive code generation language models.
- code-eval: A framework for the evaluation of autoregressive code generation language models on HumanEval.
-
Evaluating Large Language Models Trained on Code
Preprint
[Paper] Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde de Oliveira Pinto. et al. 2021.07
-
CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis
ICLR23
[Paper] Erik Nijkamp, Bo Pang, Hiroaki Hayashi, Lifu Tu, Huan Wang, Yingbo Zhou, Silvio Savarese, Caiming Xiong. 2022.03
-
ERNIE-Code: Beyond English-Centric Cross-lingual Pretraining for Programming Languages
ACL23 (Findings)
[Paper][Repo] Yekun Chai, Shuohuan Wang, Chao Pang, Yu Sun, Hao Tian, and Hua Wu. 2022.12
-
SantaCoder: don't reach for the stars!
Preprint
[Paper] Loubna Ben Allal, Raymond Li, Denis Kocetkov, Chenghao Mou, Christopher Akiki, Carlos Munoz Ferrandis, Niklas Muennighoff. et al. 2023.01
-
CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Evaluations on HumanEval-X
Preprint
[Paper] Qinkai Zheng, Xiao Xia, Xu Zou, Yuxiao Dong, Shan Wang, Yufei Xue, Zihan Wang, Lei Shen, Andi Wang, Yang Li, Teng Su, Zhilin Yang, Jie Tang. 2023.03
-
CodeGen2: Lessons for Training LLMs on Programming and Natural Languages
ICLR23
[Paper] Erik Nijkamp, Hiroaki Hayashi, Caiming Xiong, Silvio Savarese, Yingbo Zhou. 2023.05
-
StarCoder: may the source be with you!
Preprint
[Paper] Raymond Li, Loubna Ben Allal, Yangtian Zi, Niklas Muennighoff, Denis Kocetkov, Chenghao Mou. et al. 2023.05
-
CodeT5+: Open Code Large Language Models for Code Understanding and Generation
Preprint
[Paper] Yue Wang, Hung Le, Akhilesh Deepak Gotmare, Nghi D.Q. Bui, Junnan Li, Steven C.H. Hoi. 2023.05
-
Textbooks Are All You Need
Preprint
[Paper] Suriya Gunasekar, Yi Zhang, Jyoti Aneja, Caio César Teodoro Mendes, Allie Del Giorno, Sivakanth Gopi. et al. 2023.06
-
Code Llama: Open Foundation Models for Code
Preprint
[Paper] Baptiste Rozière, Jonas Gehring, Fabian Gloeckle, Sten Sootla, Itai Gat. et al. 2023.08
-
DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence
Preprint
[Paper] Daya Guo, Qihao Zhu, Dejian Yang, Zhenda Xie, Kai Dong, Wentao Zhang, Guanting Chen et al. 2024.01
-
StarCoder 2 and The Stack v2: The Next Generation
Preprint
[Paper] Anton Lozhkov, Raymond Li, Loubna Ben Allal, Federico Cassano, Joel Lamy-Poirier, Nouamane Tazi, Ao Tang et al. 2024.02
-
Code Alpaca: An Instruction-following LLaMA Model trained on code generation instructions
[Repo] Sahil Chaudhary. 2023
-
WizardCoder: Empowering Code Large Language Models with Evol-Instruct
Preprint
[Paper] Ziyang Luo, Can Xu, Pu Zhao, Qingfeng Sun, Xiubo Geng, Wenxiang Hu, Chongyang Tao, Jing Ma, Qingwei Lin, Daxin Jiang. 2023.07
-
OctoPack: Instruction Tuning Code Large Language Models
Preprint
[Paper][Repo] Niklas Muennighoff, Qian Liu, Armel Zebaze, Qinkai Zheng, Binyuan Hui, Terry Yue Zhuo, Swayam Singh, Xiangru Tang, Leandro von Werra, Shayne Longpre. 2023.08
-
Magicoder: Source Code Is All You Need
Preprint
[Paper][Repo] Yuxiang Wei, Zhe Wang, Jiawei Liu, Yifeng Ding, Lingming Zhang 2023.12
-
CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning
NeurIPS22
[Paper] Hung Le, Yue Wang, Akhilesh Deepak Gotmare, Silvio Savarese, Steven C.H. Hoi. 2022.07
-
Execution-based Code Generation using Deep Reinforcement Learning
TMLR23
[Paper] Parshin Shojaee, Aneesh Jain, Sindhu Tipirneni, Chandan K. Reddy. 2023.01
-
RLTF: Reinforcement Learning from Unit Test Feedback
Preprint
[Paper] Jiate Liu, Yiqin Zhu, Kaiwen Xiao, Qiang Fu, Xiao Han, Wei Yang, Deheng Ye. 2023.07
-
PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback
Preprint
[Paper] Bo Shen, Jiaxin Zhang, Taihong Chen, Daoguang Zan, Bing Geng, An Fu, Muhan Zeng, Ailun Yu, Jichuan Ji, Jingyang Zhao, Yuenan Guo, Qianxiang Wang. 2023.07
-
CodeT: Code Generation with Generated Tests
ICLR23
[Paper] Bei Chen, Fengji Zhang, Anh Nguyen, Daoguang Zan, Zeqi Lin, Jian-Guang Lou, Weizhu Chen. 2022.07
-
Coder Reviewer Reranking for Code Generation
ICML23
[Paper] Tianyi Zhang, Tao Yu, Tatsunori B Hashimoto, Mike Lewis, Wen-tau Yih, Daniel Fried, Sida I Wang. 2022.11
-
LEVER: Learning to Verify Language-to-Code Generation with Execution
ICML23
[Paper] Ansong Ni, Srini Iyer, Dragomir Radev, Ves Stoyanov, Wen-tau Yih, Sida I. Wang, Xi Victoria Lin. 2023.02
-
Teaching Large Language Models to Self-Debug
Preprint
[Paper] Xinyun Chen, Maxwell Lin, Nathanael Schärli, Denny Zhou. 2023.06
-
Demystifying GPT Self-Repair for Code Generation
Preprint
[Paper] Theo X. Olausson, Jeevana Priya Inala, Chenglong Wang, Jianfeng Gao, Armando Solar-Lezama. 2023.06
-
SelfEvolve: A Code Evolution Framework via Large Language Models
Preprint
[Paper] Shuyang Jiang, Yuhao Wang, Yu Wang. 2023.06
-
Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-step
ACL24
[Paper] Li Zhong, Zilong Wang, Jingbo Shang. 2024.02
-
Measuring Coding Challenge Competence With APPS
NeurIPS21
Named APPS
[Paper][Repo] Dan Hendrycks, Steven Basart, Saurav Kadavath, Mantas Mazeika, Akul Arora, Ethan Guo, Collin Burns, Samir Puranik, Horace He, Dawn Song, Jacob Steinhardt. 2021.05
-
Program Synthesis with Large Language Models
Preprint
Named MBPP
[Paper] Jacob Austin, Augustus Odena, Maxwell Nye, Maarten Bosma, Henryk Michalewski, David Dohan, Ellen Jiang, Carrie Cai, Michael Terry, Quoc Le, Charles Sutton. 2021.08
-
DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation
ICML23
[Paper] Yuhang Lai, Chengxi Li, Yiming Wang, Tianyi Zhang, Ruiqi Zhong, Luke Zettlemoyer, Scott Wen-tau Yih, Daniel Fried, Sida Wang, Tao Yu. 2022.11
-
RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems
Preprint
[Paper] Tianyang Liu, Canwen Xu, Julian McAuley. 2023.06
-
Can ChatGPT replace StackOverflow? A Study on Robustness and Reliability of Large Language Model Code Generation
Preprint
[Paper] Li Zhong, Zilong Wang. 2023.08
-
RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation
EMNLP23
[Paper] Fengji Zhang, Bei Chen, Yue Zhang, Jacky Keung, Jin Liu, Daoguang Zan, Yi Mao, Jian-Guang Lou, Weizhu Chen. 2023.10
-
CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion
Neurips23
[Paper] Yangruibo Ding, Zijian Wang, Wasi Uddin Ahmad, Hantian Ding, Ming Tan, Nihal Jain, Murali Krishna Ramanathan. et al. 2023.11
-
SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
ICLR24
[Paper] YCarlos E. Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, Karthik Narasimhan. 2023.10
-
DevBench: A Comprehensive Benchmark for Software Development
Preprint
[Paper][Repo] Bowen Li, Wenhan Wu, Ziwei Tang, Lin Shi, John Yang, Jinyang Li, Shunyu Yao, Chen Qian, Binyuan Hui, Qicheng Zhang, Zhiyin Yu, He Du, Ping Yang, Dahua Lin, Chao Peng, Kai Chen 2024.3
-
LongCoder: A Long-Range Pre-trained Language Model for Code Completion
ICML23
[Paper] Daya Guo, Canwen Xu, Nan Duan, Jian Yin, Julian McAuley. 2023.10
-
Coeditor: Leveraging Contextual Changes for Multi-round Code Auto-editing
Preprint
[Paper] Jiayi Wei, Greg Durrett, Isil Dillig. 2023.5
-
Automating Code Review Activities by Large-Scale Pre-training
Preprint
[Paper] JZhiyu Li, Shuai Lu, Daya Guo, Nan Duan, Shailesh Jannu, Grant Jenks, Deep Majumder, Jared Green, Alexey Svyatkovskiy, Shengyu Fu, Neel Sundaresan. 2022.10
-
BioCoder: A Benchmark for Bioinformatics Code Generation with Large Language Models
ISMB 2024
[Paper] Xiangru Tang, Bill Qian, Rick Gao, Jiakang Chen, Xinyun Chen, Mark Gerstein. 2023.08
-
Awesome-DevAI: A list of resources about using LLMs while building software
Awesome
[Repo] Ty Dunn, Nate Sesti. 2023.10
This is an active repository and your contributions are always welcome! If you have any question about this opinionated list, do not hesitate to contact me huybery@gmail.com
.
@software{awesome-code-llm,
author = {Binyuan Hui},
title = {An awesome and curated list of best code-LLM for research},
howpublished = {\url{https://github.com/huybery/Awesome-Code-LLM}},
year = 2023,
}
This project is inspired by Awesome-LLM.