Kimi K3 faces Claude Opus 5 in a one-image 3D world-building test
Prompt Engineering · youtube · 2026-07-29
- The video tests newly released Kimi K3 weights against Claude Opus 5 on a long-horizon task: generating a fully explorable 3D world from a single reference image.
- The workflow uses Cline as an open-source agent harness with IDE/CLI/SDK options and runs the same prompt with high reasoning effort.
- The tester reviews iterative checkpoints as Kimi K3 refines visuals, physics, interactions, materials, and scene fidelity.
- Takeaway: Kimi K3 is portrayed as a strong open-weight workhorse, while Opus 5 / Fable 5 still lead on design-heavy results.
More from Models
- Reflection AI open-sources Beam under Apache 2.0 with 40+ ecosystem partners — zhyncs42 · 2026-10-16
- Why are sub-15B open models so rare now? Labs seem to have settled on 24-27B minimum — Hot_Example_4456 · 2026-10-16
- User spots model openly generating "ideal responses" to train other models — liminal_bardo · 2026-10-16
- Reflection releases open MoE Beam-1.0: 501B total/23B active, 1M context, 3x fewer reasoning tokens — jacek2023 · 2026-10-16
- Reflection's 501B MoE Beam hits 463 tok/s on 8x GB200 with NVFP4 at day 0 — zhyncs42 · 2026-10-16
- Gemma 4 31B QAT on one 24GB card: 46 tok/s plain, ~80 with draft model on RTX 4090 — Subject_Poet_3861 · 2026-10-16