Golden Gate bridge by Kimi 2.7 on c33d benchmark - Kimi 2.7 did a good job to design the graph representing the bridge given a direct prompt to make a Golden Gate bridge
Gemma @googlegemma making a bee on c33d
kimi 2.7 @Kimi_Moonshot making a bee on c33d
when asked to add details to initial output qwen 3.5 does really good in newest version of c33d bench
bee by nemotron 3 super @nvidiaai
@jensenhuang u want to see this os ai harness system
Replying to @c33dbench
@c33dbench is an Artificial Parametric Design Project where LLM is prompted to design 3D objects, shapes, structures, geometries - and the output is a graph based, non-destructive, editable 3D model.
Heres the most interesting output yet by Kimi 2.7 @kimi_moonshot @kimidevs when asked to build own memory palace and it was way ahead of any other open source frontier model - only glm 5.2 made a working graph visible in 3D - other models such as nemotron super, minimax m3, qwen 3.5, deepseek v4 flash - failed - ran via ollama at the local run of C33D bench.
Cc @Blender @AutodeskRevit @dynamobim @McNeelEurope @RhinoGrass @nvidiaai
C33D on @RobinhoodCrypto chain
0x412bf6ABA5C55533C89C15712713Bd90e2aDabA3
github.com/3esign/c33d
browser-based, AI-native parametric CAD system. You describe an object in chat, and an LLM agent architects it as a node graph.
Procedural forest by c33d benchmark by glm 5.2 and deep seek v4 flash via @ollama - other frontier ai os models failed


























