Skip to main content

Change Log

Version: 2024-09-05​

deepseek-coder & deepseek-chat Upgraded to DeepSeek V2.5 Model​

The DeepSeek V2 Chat and DeepSeek Coder V2 models have been merged and upgraded into the new model, DeepSeek V2.5.

For backward compatibility, API users can access the new model through either deepseek-coder or deepseek-chat.

The new model significantly surpasses the previous versions in both general capabilities and code abilities.

The new model better aligns with human preferences and has been optimized in various areas such as writing tasks and instruction following:

  • ArenaHard win rate improved from 68.3% to 76.3%
  • AlpacaEval 2.0 LC win rate increased from 46.61% to 50.52%
  • MT-Bench score rose from 8.84 to 9.02
  • AlignBench score increased from 7.88 to 8.04

The new model has further enhanced its code generation capabilities based on the original Coder model, optimized for common programming application scenarios, and achieved the following results on the standard test set:

  • HumanEval: 89%
  • LiveCodeBench (January-September): 41%

Version: 2024-08-02​

API Launches Context Caching on Disk Technology​

The DeepSeek API has innovatively adopted hard disk caching, reducing prices by another order of magnitude.

For more details on the update, please refer to the documentation Context Caching is Available 2024/08/02.

Version：2024-07-25​

New API Features​

  • Update API /chat/completions
    • JSON Mode
    • Function Calling
    • Chat Prefix Completion（Beta）
    • 8K max_tokens（Beta）
  • New API /completions
    • FIM Completion（Beta）

For more details, please check the documentation New API Features 2024/07/25

Version: 2024-07-24​

deepseek-coder​

The deepseek-coder model has been upgraded to DeepSeek-Coder-V2-0724.

Version: 2024-06-28​

deepseek-chat​

The deepseek-chat model has been upgraded to DeepSeek-V2-0628.

Model's reasoning capabilities have improved, as shown in relevant benchmarks:

  • Coding: HumanEval Pass@1 79.88% -> 84.76%
  • Mathematics: MATH ACC@1 55.02% -> 71.02%
  • Reasoning: BBH 78.56% -> 83.40%

In the Arena-Hard evaluation, the win rate against GPT-4-0314 increased from 41.6% to 68.3%.

The model's role-playing capabilities have significantly enhanced, allowing it to act as different characters as requested during conversations.

Version: 2024-06-14​

deepseek-coder​

The deepseek-coder model has been upgraded to DeepSeek-Coder-V2-0614, significantly enhancing its coding capabilities. It has reached the level of GPT-4-Turbo-0409 in code generation, code understanding, code debugging, and code completion. Additionally, it possesses excellent mathematical and reasoning abilities, and its general capabilities are on par with DeepSeek-V2-0517.

Version: 2024-05-17​

deepseek-chat​

The deepseek-chat model has been upgraded to DeepSeek-V2-0517. The model has seen a significant improvement in following instructions, with the IFEval Benchmark Prompt-Level accuracy jumping from 63.9% to 77.6%. Additionally, on API end, we have optimized model ability to follow instruction filled in the ``system" part. This optimization has significantly elevated the user experience across a variety of tasks, including immersive translation, Retrieval-Augmented Generation (RAG), and more.

The model's accuracy in outputting JSON format has been enhanced. In our internal test set, the JSON parsing rate increased from 78% to 85%. By introducing appropriate regular expressions, the JSON parsing rate was further improved to 97%.