Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d271Policy30d66, 14 pendingSources1,015

Kimi K2 Instruct

MoonshotReleased Sep 5, 2025Current

Score basis

Kimi K2 Instruct is behind the leaders in long context, factuality, and agentic tasks. Too few results yet to rate reasoning, coding, safety, math, multimodal tasks, multilingual tasks, or instruction following.

Capability profile

Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.

Limited3 capabilities
  1. Long Context−35.0%1 of 3
  2. Factuality−37.6%3 of 4
  3. Agentic−43.5%2 of 7
Not rated7 capabilities

Too few results yet to rate Reasoning, Coding, Safety, Math, Multimodal, Multilingual or Instruction Following.

Price

$0.60input$2.50outputper million tokens

From Artificial Analysis · 3 providers tracked · All prices

Costs more than 60% of 330 priced models · 3:1 input-to-output blend, log scale

Evidence

152results on89benchmarks

  • 15 independently verified
  • 15 aggregator
  • 101 vendor-reported
  • 21 cross-referenced

From 17 sources · latest Oct 8, 2026 · How verification works

API features

Tool callingStructured outputs

As listed by OpenRouter

Kimi K2 Instruct benchmark results

152 results on 89 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.

Long Context

LimitedFull long context ranking

35.0% behind the leader1 of 3 ranked benchmarks measured

Factuality

LimitedFull factuality ranking

37.6% behind the leader3 of 4 ranked benchmarks measured

Agentic

LimitedFull agentic ranking

43.5% behind the leader2 of 7 ranked benchmarks measured

Show 1 more agentic resultHide 1 agentic result

Reasoning

Not enough dataFull reasoning ranking

0 of 6 ranked benchmarks measured

Show 7 more reasoning resultsHide 7 reasoning results

Coding

Not enough dataFull coding ranking

0 of 10 ranked benchmarks measured

Show 18 more coding resultsHide 18 coding results

Math

Not enough dataFull math ranking

0 of 5 ranked benchmarks measured

Instruction Following

Not enough dataFull instruction following ranking

0 of 3 ranked benchmarks measured

Show 1 more instruction following resultHide 1 instruction following result

More results

Benchmarks outside the capability baskets. They are not ranked against a leader.

Show 103 more resultsHide 103 results

Kimi K2 Instruct: common questions

Who makes Kimi K2 Instruct?

Kimi K2 Instruct is made by Moonshot.

When was Kimi K2 Instruct released?

Kimi K2 Instruct was released on Sep 5, 2025, according to Artificial Analysis.

What is Kimi K2 Instruct good at?

Kimi K2 Instruct is behind the leaders in long context, factuality, and agentic tasks. Too few results yet to rate reasoning, coding, safety, math, multimodal tasks, multilingual tasks, or instruction following.

How much does Kimi K2 Instruct cost?

Kimi K2 Instruct costs $0.60 per million input tokens and $2.50 per million output tokens, according to Artificial Analysis. We track its price at 3 providers. At a mix of three input tokens to one output token, it costs more than 60% of the 330 priced models we track.

How many benchmarks has Kimi K2 Instruct been tested on?

We track 152 results for Kimi K2 Instruct on 89 benchmarks from 17 sources, 15 of them independently verified. The latest was recorded on Oct 8, 2026.

Which API features does Kimi K2 Instruct support?

OpenRouter lists tool calling and structured outputs for Kimi K2 Instruct.

About this record

Where Kimi K2 Instruct's numbers come from, and every name it appears under.

Tracked since
May 1, 2026
Newest source mention
Sep 2, 2026

Where the results come from

Verification: 152 scores · 15 independently verified · 15 aggregator-attributed · 21 vendor cross-reference · 101 vendor-reported. How these tiers are assigned

From 17 sources on 7 sites. Hugging Face supplies 66 of them; the 15 independently verified results come from 5 sites. Bars are coloured by trust tier.

  • huggingface.co66
  • api.llm-stats.com56
  • artificialanalysis.ai17
  • storage.googleapis.com6
  • raw.githubusercontent.com4
  • swebench.com2
  • labs.scale.com1

Also known as

K2-Instruct-0711Kimi K2 Instruct 0905openhands + kimi k2kimi-k2-0905