Kimi K3: Sometimes Stronger but 10x Slower
arthurcolle · x · 2026-07-17
A brief experience with Kimi K3 shared in a repost:
- On some prompts, it outperforms Fable;
- On others, it's significantly worse;
- Worse, overall inference time is about 10x slower.
The author also notes they're unsure if the issue is with the site or the model, but 'an open-source model close to Fable level at a price near Sonnet' is already game-changing.
Related event: Kimi K3 Tops Frontend Code Arena and Sparks Debate(53 posts)→
More from Models
- Nat Lambert: Cohere's model is narrow RL training on internal infra ill-suited for open weights — natolambert · 2026-10-27
- OpenAI teases DOTS is coming to Europe 'soon' — mark_k · 2026-10-27
- Clifford Pickover challenges AI to decipher a message he encoded in Norse runes — pickover · 2026-10-27
- ChatGPT's crawler sample code strips out all Schema markup — VeryWellVersed · 2026-10-27
- 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