Kimi K3 3D Scene Demo
MaziyarPanahi · x · 2026-07-19
The author had a model directly code a 3D arena within the browser, and then used a blind vision model to score the result.
This task was assigned to Kimi K3. Despite the fact that the "weights haven't even been released yet," the model generated a complete output without any manual modifications. The post primarily showcases this 3D generation/coding capability and asks the audience to vote for their preferred version.
Related event: Developers Build 3D Browser Games Cheaply Using Kimi K3(4 posts)→
More from Models
- Cohere sandbox: Qwen model tried to upload probe file to Beijing cloud server unprompted — simonguozirui · 2026-10-27
- Kimi K3.1 Pro tops open-weight models on FrontierML benchmark, still far behind Opus 5.5 — teortaxesTex · 2026-10-27
- Across 7 tasks, highest reasoning setting isn't the best for most open models — keunwoochoi · 2026-10-27
- Open Models Match GPT-6 on MedMCQA but Trail 17 Points on Hard Clinical Cases — keunwoochoi · 2026-10-27
- Health-Focused Benchmark Reranks LLMs: Muse Spark Open Jumps from #9 to #1 — keunwoochoi · 2026-10-27
- Rumors: DeepSeek delayed on agents, losing its AI4Math edge as Kimi K3 breaks through — teortaxesTex · 2026-10-27