Kimi K2.6
Open-source 1T MoE that runs coding agents nonstop for 13 hours
The Panel's Take
Moonshot AI open-sourced Kimi K2.6 on April 20, 2026 — a trillion-parameter Mixture-of-Experts model with 32B active parameters, 256K context, and native vision. It is available on Kimi Chat, the API, and the Kimi Code CLI, with weights published on Hugging Face under a Modified MIT License. The headline feature is long-horizon execution: K2.6 can pursue a real engineering goal autonomously for up to 13 continuous hours without stopping to ask for direction. The model's Agent Swarm mode now scales to 300 simultaneous sub-agents coordinating across 4,000 steps — up from 100 agents and 1,500 steps in the previous generation. A new "Claw Groups" research preview lets agents on different devices and different underlying models collaborate with a human in a shared workspace. On SWE-Bench Pro, K2.6 scores 58.6, edging out GPT-5.4 (57.7) and landing above Claude Opus 4.6. On Humanity's Last Exam with tools it scores 54.0, leading every model in the comparison. For teams that want frontier agentic coding power without an API bill tied to a single vendor, Kimi K2.6 is the clearest open-weights option available right now.
Share this verdict
Kimi K2.6 verdict: SHIP 🚀 3 ships · 1 skip from the expert panel Full review: shiporskip.io/tool/kimi-k26-moonshot-ai-1t-moe-open-source-agent-swarm-2026
Weekly AI Tool Verdicts
Get the next verdict in your inbox
7 critics review a new AI tool every day. Weekly digest — free.
Compare Kimi K2.6 with Others
Embed this verdict
Tool makers can add a live ShipOrSkip badge to their site. Badge loads track impressions; clicks route back to this review.
<a href="https://shiporskip.io/api/badge-click/kimi-k26-moonshot-ai-1t-moe-open-source-agent-swarm-2026" target="_blank" rel="noopener"><img src="https://shiporskip.io/api/badge/kimi-k26-moonshot-ai-1t-moe-open-source-agent-swarm-2026" alt="Kimi K2.6 Ship verdict on ShipOrSkip" width="360" height="90" /></a>[](https://shiporskip.io/api/badge-click/kimi-k26-moonshot-ai-1t-moe-open-source-agent-swarm-2026)<iframe src="https://shiporskip.io/embed/kimi-k26-moonshot-ai-1t-moe-open-source-agent-swarm-2026" title="Kimi K2.6 ShipOrSkip verdict" width="360" height="260" style="border:0;border-radius:16px;max-width:100%;" loading="lazy"></iframe>The reviews
“13 hours of autonomous coding without a babysitter is a genuine workflow unlock. The 300-agent swarm plus 256K context means I can throw an entire monorepo at it and actually trust the output. Modified MIT is permissive enough to build a product on.”
“Trillion-parameter open weights sound exciting until you price out the H100s needed to run them. Most teams will use the API anyway, which puts them right back in vendor-dependency land. The benchmark lead over GPT-5.4 is razor-thin — two decimal points on a leaderboard isn't a moat.”
“A 1T open-weights model that beats closed frontier models at agentic coding is a landmark moment. This is what the open-source AI ecosystem needed: proof that small labs can ship at the frontier without hundreds of billions in capital. Expect every serious enterprise AI stack to test K2.6 within 60 days.”
“The 'Claw Groups' multi-device collaboration preview is quietly the most interesting part — the idea of a human co-creating alongside a swarm of agents in a shared workspace opens up entirely new creative production pipelines. Early, but I'm watching it closely.”