Moonshot Releases and Open-Sources Kimi K3
heyshrutimishra · x · 2026-07-17
Moonshot has launched Kimi K3, branded as "Open Frontier Intelligence."
- The model features 2.8 trillion parameters, is natively multimodal, and supports a 1 million token context.
- The team claims it excels in long-context reasoning and agentic coding tasks, noting that Kimi Delta Attention can boost decoding speeds for million-token contexts by up to 6.3x.
- Training utilizes Attention Residuals, reportedly improving training efficiency by about 25% with an additional cost of less than 2%.
- The model is now available on the Kimi website, Kimi Work, Kimi Code, and via API.
- Open Weights are scheduled for release on 2026-07-27.
- External observations highlighted strong performance on benchmarks like SWE-Bench Pro, SWE-bench Multilingual, BrowseComp, and Toolathlon, alongside highly competitive inference pricing.
Related event: Kimi K3 Triggers a Reassessment of Chinese Frontier AI(94 posts)→
More from Models
- 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
- Opus Refuses Protein Research Codebase Over 'Safety' Concerns, Dev Considers Rolling His Own — josephdviviano · 2026-09-11