Blender's UI and Runtime: Much Faster Than GPUI
A GitHub project claims Blender's UI and runtime are much faster than GPUI.
11 stories, newest first · one card per story
A GitHub project claims Blender's UI and runtime are much faster than GPUI.
Reviewer-model feedback on renders helps more than extra reasoning or an agent harness, and can lift a 27B model past a 2.8T model's single-shot rate.
CinemaBench covers 150 Blender scenes, 750 text-directed tasks, and 60 reference videos.
GPT-6-Astra scored 79.9 overall, ahead of Opus-5 at 73.0 and GPT-5.6-Sol at 67.7.
Across 26 models, documentation is strong for in-frame text but weak for measurements and small spatial relations.
Code2Games helps coding agents generate consistent game worlds and adapt them to Unreal Engine 5.

LEGO-Anything has coding agents write Blender scenes from one photo, but they cannot reliably judge geometric accuracy.
LEGO-Anything uses coding agents to rebuild editable 3D scenes as executable Blender programs.
Blender-VideoBench evaluates agentic video understanding by having agents programmatically reconstruct real videos in Blender scenes.
Simon Willison demos a .blend URL viewer built with GPT-6 Astra in Codex and ChatGPT Images 2.5 generating Blender models.
Simon Willison demonstrates driving the Blender macOS app with ChatGPT Codex coding agents to render scenes via Python, costing roughly $4.24 at API rates.
Today 1.6K readers · 2.4K views · 775 reads · all time 189K views