Kimi K2.6

Open (Restricted)

Parameters

256K

Context

Benchmarks

About Kimi K2.6

Kimi K2.6 is an AI model developed by Moonshot, released in 2026, made available as an open-weights model with 1000B params. Kimi K2.6 is Moonshot AI's upgrade to K2.5 — an open-weight 1T-parameter Mixture-of-Experts model with 32B active per to.

On this page you'll find Kimi K2.6's full specifications, including a context window of 256K tokens, 8 benchmark results. Review provider pricing and benchmark scores below, or compare Kimi K2.6 head-to-head with other AI models.

→ More models by Moonshot → AI benchmarks leaderboard

Links

Announcement ↗ Hugging Face ↗

Community

Would you run Kimi K2.6 again?

No votes yet — be the first.

Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

Kimi K2.6 benchmark scores▶

Compare on the benchmark table →

Benchmark	Category	Score	Variant
BrowseComp	agentic	83.2%
Terminal-Bench 2.0	agentic	66.7%
HumanEval	code	93.8%	pass@1
SWE-bench Pro	code	58.6%	agentic
SWE-bench Verified	code	80.2%	agentic
MMLU-Pro	general	82.5%
AIME 2025	math	82.9%
Humanity's Last Exam	reasoning	50.2%	with-tools

More models like Kimi K2.6

Frequently asked questions

What is Kimi K2.6? ▶

Kimi K2.6 is Moonshot AI's upgrade to K2.5 — an open-weight 1T-parameter Mixture-of-Experts model with 32B active per to It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created Kimi K2.6? ▶

Kimi K2.6 was developed by Moonshot and released in 2026.

Is Kimi K2.6 open source or proprietary? ▶

Kimi K2.6 ships as an open-weights model: you can download and self-host the weights, though the licence may place some restrictions on use.

What is Kimi K2.6's context window? ▶

Kimi K2.6 supports a context window of 256K tokens, and has 1000B params.

How much does Kimi K2.6 cost? ▶

Pricing for Kimi K2.6 depends on the provider. See the providers table on this page for the latest API rates.

How does Kimi K2.6 perform on benchmarks? ▶

Kimi K2.6 is benchmarked across 8 evaluations on GenAIList, including BrowseComp (83.2%). See the full benchmark table below and compare it with other models.