DeepSeek 将 deepseek-chat 升级至 DeepSeek-V3-0324

deepseek-chat

AI 导读

DeepSeek 将 deepseek-chat 模型升级为 DeepSeek-V3-0324，推理能力显著提升，MMLU-Pro 从 75.9 升至 81.2，GPQA 从 59.1 升至 68.4，AIME 从 39.6 升至 59.4，LiveCodeBench 从 39.2 升至 49.2。

推荐理由

官方给出 V3-0324 在推理、编码与中文写作上的基准变化，可据此判断升级幅度。

正文 · 原文

deepseek-chat Model Upgraded to DeepSeek-V3-0324:

Enhanced Reasoning Capabilities
- Significant improvements in benchmark performance:
  - MMLU-Pro: 75.9 → 81.2 (+5.3)
  - GPQA: 59.1 → 68.4 (+9.3)
  - AIME: 39.6 → 59.4 (+19.8)
  - LiveCodeBench: 39.2 → 49.2 (+10.0)
Optimized Front-End Web Development
- Improved accuracy in code generation
- More aesthetically pleasing web pages and game front-ends
Upgraded Chinese Writing Proficiency
- Enhanced style and content quality:
  - Aligned with the R1 writing style
  - Better quality in medium-to-long-form writing
Feature Enhancements
- Improved multi-turn interactive rewriting
- Optimized translation quality and letter writing
Improved Chinese Search Capabilities
- Enhanced report analysis requests with more detailed outputs
Function Calling Improvements
- Increased accuracy in Function Calling, fixing issues from previous V3 versions

来源：DeepSeek API News · api-docs.deepseek.com