deepseek-ai/DeepSeek-Coder-V2

deepseek-ai/DeepSeek-Coder-V2

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

License: MIT

Stars: 6833

Forks: 1087

Open issues: 72

Created: 2024-06-14T03:39:37Z

Pushed: 2025-11-11T06:44:45Z

Default branch: main

Fork: no

Archived: no

README:

Model Download | Evaluation Results | API Platform | How to Use | License | Citation

Paper Link👁️

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

1. Introduction

We present DeepSeek-Coder-V2, an open-source Mixture-of-Experts (MoE) code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks. Specifically, DeepSeek-Coder-V2 is further pre-trained from an intermediate checkpoint of DeepSeek-V2 with additional 6 trillion tokens. Through this continued pre-training, DeepSeek-Coder-V2 substantially enhances the coding and mathematical reasoning capabilities of DeepSeek-V2, while maintaining comparable performance in general language tasks. Compared to DeepSeek-Coder-33B, DeepSeek-Coder-V2 demonstrates significant advancements in various aspects of code-related tasks, as well as reasoning and general capabilities. Additionally, DeepSeek-Coder-V2 expands its support for programming languages from 86 to 338, while extending the context length from 16K to 128K.

In standard benchmark evaluations, DeepSeek-Coder-V2 achieves superior performance compared to closed-source models such as GPT4-Turbo, Claude 3 Opus, and Gemini 1.5 Pro in coding and math benchmarks. The list of supported programming languages can be found [here](supported_langs.txt).

2. Model Downloads

We release the DeepSeek-Coder-V2 with 16B and 236B parameters based on the DeepSeekMoE framework, which has actived parameters of only 2.4B and 21B , including base and instruct models, to the public.

3. Evaluation Results

3.1 Code Generation

| | #TP | #AP | HumanEval | MBPP+ | LiveCodeBench | USACO | |:------------|:--------:|:--------:|:--------:|:--------:|:--------:|:-----------:| | Closed-Source Models | | | | | | | | Gemini-1.5-Pro | - | - | 83.5 | 74.6 | 34.1 | 4.9 | | Claude-3-Opus | - | - | 84.2 | 72.0 | 34.6 | 7.8 | | GPT-4-Turbo-1106 | - | - | 87.8 | 69.3 | 37.1 | 11.1 | | GPT-4-Turbo-0409 | - | - | 88.2 | 72.2 | 45.7 | 12.3 | | GPT-4o-0513 | - | - | 91.0 | 73.5 | 43.4 | 18.8 | | Open-Source Models | | | | | | | | CodeStral | 22B | 22B | 78.1 | 68.2 | 31.0 | 4.6 | | DeepSeek-Coder-Instruct | 33B | 33B | 79.3 | 70.1 | 22.5 | 4.2 | | Llama3-Instruct | 70B | 70B | 81.1 | 68.8 | 28.7 | 3.3 | | DeepSeek-Coder-V2-Lite-Instruct | 16B | 2.4B | 81.1 | 68.8 | 24.3 | 6.5 | | DeepSeek-Coder-V2-Instruct | 236B | 21B | 90.2 | 76.2 | 43.4 | 12.1 |

3.2 Code Completion

| Model | #TP | #AP | RepoBench (Python) | RepoBench (Java) | HumanEval FIM | | :------------------------------ | :--: | :--: | :----------------: | :--------------: | :-----------: | | CodeStral | 22B | 22B | 46.1 | 45.7 | 83.0 | | DeepSeek-Coder-Base | 7B | 7B | 36.2 | 43.3 | 86.1 | | DeepSeek-Coder-Base | 33B | 33B | 39.1 | 44.8 | 86.4 | | DeepSeek-Coder-V2-Lite-Base | 16B | 2.4B | 38.9 | 43.3 | 86.4 |

3.3 Code Fixing

| | #TP | #AP | Defects4J | SWE-Bench | Aider | | ----------------------------------- | :--: | :--: | :-------: | :-------: | :------: | | Closed-Source Models | | | | | | | Gemini-1.5-Pro | - | - | 18.6 | 19.3 | 57.1 | | Claude-3-Opus | - | - | 25.5 | 11.7 | 68.4 | | GPT-4-Turbo-1106 | - | - | 22.8 | 22.7 | 65.4 | | GPT-4-Turbo-0409 | - | - | 24.3 | 18.3 | 63.9 | | GPT-4o-0513 | - | - | 26.1 | 26.7 | 72.9 | | Open-Source Models | | | | | | | CodeStral | 22B | 22B | 17.8 | 2.7 | 51.1 | | DeepSeek-Coder-Instruct | 33B | 33B | 11.3 | 0.0 | 54.5 | | Llama3-Instruct | 70B | 70B | 16.2 | - | 49.2 | | DeepSeek-Coder-V2-Lite-Instruct | 16B | 2.4B | 9.2 | 0.0 | 44.4 | | DeepSeek-Coder-V2-Instruct | 236B | 21B | 21.0 | 12.7 | 73.7 |

3.4 Mathematical Reasoning

| | #TP | #AP | GSM8K | MATH | AIME 2024 | Math Odyssey | | ----------------------------------- | :--: | :--: | :------: | :------: | :-------: | :----------: | | Closed-Source Models | | | | | | | | Gemini-1.5-Pro | - | - | 90.8 | 67.7 | 2/30 | 45.0 | | Claude-3-Opus | - | - | 95.0 | 60.1 | 2/30 | 40.6 | | GPT-4-Turbo-1106 | - | - | 91.4 | 64.3 | 1/30 | 49.1 | | GPT-4-Turbo-0409 | - | - | 93.7 | 73.4 | 3/30 | 46.8 | | GPT-4o-0513 | - | - | 95.8 | 76.6 | 2/30 | 53.2 | | Open-Source Models | | | | | | | | Llama3-Instruct | 70B | 70B | 93.0 | 50.4 | 1/30 | 27.9 | | DeepSeek-Coder-V2-Lite-Instruct | 16B | 2.4B | 86.4 | 61.8 | 0/30 | 44.4 | | DeepSeek-Coder-V2-Instruct | 236B | 21B | 94.9 | 75.7 | 4/30 | 53.7 |

3.5 General Natural Language

| Benchmark | Domain | DeepSeek-V2-Lite Chat | DeepSeek-Coder-V2-Lite Instruct | DeepSeek-V2 Chat | DeepSeek-Coder-V2 Instruct | | :------------------: | :-----: | :-------------------: | :-----------------------------: | :--------------: | :------------------------: | | BBH | English | 48.1 | 61.2 | 79.7 | 83.9 | | MMLU | English | 55.7 | 60.1 | 78.1 | 79.2 | | ARC-Easy | English | 86.1 | 88.9 | 98.1 | 97.4 | | ARC-Challenge | English | 73.4 | 77.4 | 92.3 | 92.8 | | TriviaQA | English | 65.2 | 59.5 | 86.7 | 82.3 | | NaturalQuestions | English | 35.5 | 30.8 | 53.4 | 47.5 | | AGIEval | English | 42.8 | 28.7 | 61.4 | 60 | | CLUEWSC | Chinese | 80.0 | 76.5 | 89.9 | 85.9 | | C-Eval | Chinese | 60.1 | 61.6 | 78.0 | 79.4 | | CMMLU | Chinese | 62.5 | 62.7 | 81.6 | 80.9 | | Arena-Hard | - | 11.4 | 38.1 | 41.6 | 65.0 | | AlpaceEval 2.0 | - | 16.9 | 17.7 | 38.9 | 36.9 | | MT-Bench | - | 7.37 | 7.81 | 8.97 | 8.77 | | Alignbench | - | 6.02 | 6.83 | 7.91 | 7.84 |

3.6 Context Window

Evaluation results on the `Needle In A Haystack` (NIAH) tests. DeepSeek-Coder-V2 performs well across all context window lengths up to 128K.

4. Chat Website

You can chat with the DeepSeek-Coder-V2 on DeepSeek's official website: chat.deepseek.com

5. API Platform

We also provide OpenAI-Compatible API at DeepSeek Platform:…