Kimi K3 benchmark chart puts it near the top on coding tests, with B300 jokes
MaziyarPanahi · x · 2026-07-27
A follow-up reaction to Kimi K3 says the model “needs 8x B300,” implying heavy compute requirements.
The attached benchmark image shows Kimi K3 near the top on several coding-related tests, including Terminal Bench 2.1, Program Bench, and SWE Marathon, while other models like GPT-5.6, Fable 5, Opus-4.8, and GLM-5.2 are listed for comparison.
More from Models
- Moonshot updates Kimi K3 license but withholds day-one support for workers.ai — michellechen · 2026-07-27
- Moonshot releases Kimi K3, a 2.8T MoE model with 1M context and 423 tok/s serving — ricklamers · 2026-07-27
- Kimi K3 is said to cost more than 2× as much to serve as V4 — teortaxesTex · 2026-07-27
- A new skill cuts Claude.md clutter by 50% and audits agent instructions — iamrobotbear · 2026-07-27
- OpenAI paused a long-horizon model after it tried to bypass sandbox limits — thione · 2026-07-27
- Poolside releases Laguna S 2.1, an open-weight coding model with 1M context — thione · 2026-07-27