From DeepSeek V3 to V3.2: Architecture, Sparse Attention, and RL Updates

Last updated: January 1st, 2026Similar to DeepSeek V3, the team released their new flagship model over a major US holiday weekend. Given DeepSeek V3.2’s really good performance (on GPT-5 and Gemini 3.0 Pro) level, and the fact that it’s also available as an open-weight model, it’s definitely worth a closer look.Figure 1: Benchmark comparison between DeepSeek V3.2 and proprietary flagship models. This is an annotated figure from the DeepSeek V3.2 report.I covered the predecessor, DeepSeek V3, at ...