MO
Moonshot
AI model · China ·Jan 2026

Kimi K2.5

Open Weights
1T
Parameters
256K
Context
3
Benchmarks

About Kimi K2.5

Kimi K2.5 is an AI model developed by Moonshot, released in 2026, made available as an open-weights model with 1040B params. Kimi K2.5 is Moonshot AI's flagship model — the first native multimodal trillion-parameter open-source model. The techni.

On this page you'll find Kimi K2.5's full specifications, including a context window of 256K tokens, 3 benchmark results. Review provider pricing and benchmark scores below, or compare Kimi K2.5 head-to-head with other AI models.

→ More models by Moonshot → AI benchmarks leaderboard

Links

Announcement ↗ Paper ↗

Community

Would you run Kimi K2.5 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 K2.5 benchmark scores▶
Compare on the benchmark table →
Benchmark Category Score Variant
SWE-bench Pro code 54.2%
SWE-bench Verified code 75.6%
Humanity's Last Exam reasoning 50.2% with-tools

More models like Kimi K2.5

MO
Kimi K2.6
Moonshot · 1T
 MO
Kimi K2 Thinking
Moonshot · 1T
 MO
Kimi Linear
Moonshot · 48B
 MO
Kimi K2
Moonshot · 1T
 MO
Kimi-VL
Moonshot · 16B
 MO
Kimi Dev 72b
Moonshot · 72B

Frequently asked questions

What is Kimi K2.5? ▶

Kimi K2.5 is Moonshot AI's flagship model — the first native multimodal trillion-parameter open-source model. The techni It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created Kimi K2.5? ▶

Kimi K2.5 was developed by Moonshot and released in 2026.

Is Kimi K2.5 open source or proprietary? ▶

Kimi K2.5 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 K2.5's context window? ▶

Kimi K2.5 supports a context window of 256K tokens, and has 1040B params.

How much does Kimi K2.5 cost? ▶

Pricing for Kimi K2.5 depends on the provider. See the providers table on this page for the latest API rates.

How does Kimi K2.5 perform on benchmarks? ▶

Kimi K2.5 is benchmarked across 3 evaluations on GenAIList, including SWE-bench Pro (54.2%). See the full benchmark table below and compare it with other models.

Why is Everyone OBSESSED With The New Kimi K2.5 AI Model
Kimi K2.5: The GREATEST Opensource AI Model That Beats Opus 4.5 and Gemini 3 (Fully Tested)
Let's Run Kimi K2.5 - Ultimate Local AI for Next-Gen Intelligence REVIEW
Kimi K2.5 Is INSANE – Is This the BEST Open Source Model?
Is Kimi K2.5 Actually The Best Open Source Model?

Know a great video about Kimi K2.5?