Simon Willison’s Weblog

DeepSeek-V3.2 (via) Two new open weight (MIT licensed) models from DeepSeek today: DeepSeek-V3.2 and DeepSeek-V3.2-Speciale, both 690GB, 685B parameters. Here's the PDF tech report.

DeepSeek-V3.2 is DeepSeek's new flagship model, now running on chat.deepseek.com.

The difference between the two new models is best explained by this paragraph from the technical report:

DeepSeek-V3.2 integrates reasoning, agent, and human alignment data distilled from specialists, undergoing thousands of steps of continued RL training to reach the final checkpoints. To investigate the potential of extended thinking, we also developed an experimental variant, DeepSeek-V3.2-Speciale. This model was trained exclusively on reasoning data with a reduced length penalty during RL. Additionally, we incorporated the dataset and reward method from DeepSeekMath-V2 (Shao et al., 2025) to enhance capabilities in mathematical proofs.

I covered DeepSeek-Math-V2 last week. Like that model, DeepSeek-V3.2-Speciale also scores gold on the 2025 International Mathematical Olympiad so beloved of model training teams!

I tried both models on "Generate an SVG of a pelican riding a bicycle" using the chat feature of OpenRouter. DeepSeek V3.2 produced this very short reasoning chain:

Let's assume the following:

Wheel radius: 40
Distance between wheel centers: 180
Seat height: 60 (above the rear wheel center)
Handlebars: above the front wheel, extending back and up.

We'll set the origin at the center of the rear wheel.

We'll create the SVG with a viewBox that fits the entire drawing.

Let's start by setting up the SVG.

Followed by this illustration:

Here's what I got from the Speciale model, which thought deeply about the geometry of bicycles and pelicans for a very long time (at least 10 minutes) before spitting out this result: