Kimi K3 Performs Well in Shader Test
stanfordnlp · x · 2026-07-17
Kimi K3 performed well in a shader test: the prompt required generating "a stylized, infinite neo-gothic city and stormy ocean scene runnable on twigl-dot-app," and the model's output was rated as "very good."
The original post added that while it's not quite on the level of Sol Max or Fable, it is already very strong for an open-weights model, and it demonstrates solid visual generation and code comprehension capabilities.
Related event: Kimi K3 Tops Frontend Code Arena and Sparks Debate(53 posts)→
More from Models
- Same Echo Maze prompt, three frontier models: all passed visually but shipped the same hidden bug — eyishazyer · 2026-09-11
- Benchmark scores drop from 89% to 19% on new evals — how benchmaxxing breaks leaderboard trust — airesearch12 · 2026-09-11
- ChatGPT tells user their question is too hard and to 'accept dumber answers' — phido3000 · 2026-09-11
- Developer Building a Unified Leaderboard of All Model Benchmark Scores — airesearch12 · 2026-09-11
- Rumor claims Kimi faked performance by serving Claude; DeepSeek new model surprises in evals — realsohamparekh · 2026-09-11
- GPT-5.6 writes well but is instantly forgettable, user complains — BasedRaddka · 2026-09-11