LaunchAI ModelsJuly 27, 2026
Moonshot AI releases Kimi K3, a 2.8T parameter MoE model

Kimi K3 is a 2.8T parameter MoE model featuring a 1M-token context window and native visual understanding. It achieves an 89.4% pass@4 rate on the DeepSWE benchmark, outperforming GPT-5.6 Sol while costing 64% less per task.
15 sources
Deploying Kimi K3 on AWSaws.amazon.com
unsloth/Kimi-K3huggingface.co
Kimi K3 vs GPT-5.6 Sol on DeepSWE: Cost, Coding, and Routingtogether.ai
RT @togethercompute: We analyzed Kimi K3 vs. Claude Fable 5 for software engineering tasks using...x.com
Kimi K3: The open-weights escalationinterconnects.ai
On Kimi K3: Its Capabilities And Related Discontentsthezvi.substack.com
What Is Moonshot AI’s Kimi K3 Model and Why Is It Making Waves?bloomberg.com
Moonshot AI by email
Get an email when Moonshot AI ships something
More stories today
- Thoughtworks' Kief Morris: humans must stay 'on the loop' in AI delivery
- GEMA wins major copyright ruling against Suno, orders damages paid
- LangChain builds ReviewBench benchmark for code review agents
- DeepSeek Flash 0731's reasoning trace amuses with 'OH MY GOD' outburst
- Former OpenAI VP Jerry Tworek discusses AI lab automation