Kimi K2 (Non-Reasoning)
Kimi K2 (Non-Reasoning) is behind the leaders in factuality, long context, and instruction following. Too few results yet to rate reasoning, coding, agentic tasks, safety, math, multimodal tasks, or multilingual tasks.
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.
Too few results yet to rate Reasoning, Coding, Agentic, Safety, Math, Multimodal or Multilingual.
Price
$0.57input$2.30outputper million tokens
From Artificial Analysis · All prices
Evidence
23results on21benchmarks
- 8 independently verified
- 15 aggregator
From 6 sources · latest Oct 8, 2026 · How verification works
API features
Tool callingStructured outputs
As listed by OpenRouter
Kimi K2 (Non-Reasoning) benchmark results
23 results on 21 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.
29.8% behind the leader2 of 4 ranked benchmarks measured
- AA-Omniscience · Accuracy27.35Oct 8, 2026omniscienceAccuracy
- AA-Omniscience · Non-hallucination23.38Oct 8, 2026omniscienceNonHallucination
Show 1 more factuality resultHide 1 factuality result
- Vectara HHEM hallucination ratelower is better17.90Jun 20, 2026
35.0% behind the leader1 of 3 ranked benchmarks measured
- 53.00Oct 8, 2026
44.2% behind the leader1 of 3 ranked benchmarks measured
- IFBench41.50Oct 8, 2026aa_ifbench
0 of 6 ranked benchmarks measured
- 26.30May 10, 2026
- 0.00Oct 8, 2026
- GPQA Diamond76.57Oct 8, 2026gpqa
Show 1 more reasoning resultHide 1 reasoning result
- Humanity's Last Exam7.41Oct 8, 2026aa_hle
0 of 10 ranked benchmarks measured
- Terminal-Bench Hard15.91Oct 8, 2026aa_terminalbench_hard
- SciCode34.49Sep 4, 2026aa_scicode
0 of 7 ranked benchmarks measured
- 24.60May 2, 2026
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- AA Intelligence13.00Sep 20, 2026Artificial Analysis Intelligence Index
- AA Intelligence24.00Sep 2, 2026Artificial Analysis Intelligence Index
- 59.20Jun 20, 2026
- 98.60Jun 20, 2026
- 82.10Jun 20, 2026
- 59.10May 1, 2026
Show 5 more resultsHide 5 results
- 47.90May 2, 2026
- AA Intelligence12.72Oct 8, 2026aa_intelligence_index
- -28.32Oct 8, 2026
- 34.83May 2, 2026
- τ²-Bench Telecom (AA run)61.11Oct 8, 2026aa_tau2
Kimi K2 (Non-Reasoning): common questions
Who makes Kimi K2 (Non-Reasoning)?
Kimi K2 (Non-Reasoning) is made by Moonshot.
When was Kimi K2 (Non-Reasoning) released?
Kimi K2 (Non-Reasoning) was released on Jul 11, 2025, according to Artificial Analysis.
What is Kimi K2 (Non-Reasoning) good at?
Kimi K2 (Non-Reasoning) is behind the leaders in factuality, long context, and instruction following. Too few results yet to rate reasoning, coding, agentic tasks, safety, math, multimodal tasks, or multilingual tasks.
How much does Kimi K2 (Non-Reasoning) cost?
Kimi K2 (Non-Reasoning) costs $0.57 per million input tokens and $2.30 per million output tokens, according to Artificial Analysis. At a mix of three input tokens to one output token, it costs more than 59% of the 330 priced models we track.
How many benchmarks has Kimi K2 (Non-Reasoning) been tested on?
We track 23 results for Kimi K2 (Non-Reasoning) on 21 benchmarks from 6 sources, 8 of them independently verified. The latest was recorded on Oct 8, 2026.
Which API features does Kimi K2 (Non-Reasoning) support?
OpenRouter lists tool calling and structured outputs for Kimi K2 (Non-Reasoning).
About this record
Where Kimi K2 (Non-Reasoning)'s numbers come from, and every name it appears under.
- Tracked since
- Jun 18, 2026
- Newest source mention
- Jul 20, 2026
Where the results come from
Verification: 23 scores · 8 independently verified · 15 aggregator-attributed. How these tiers are assigned
From 6 sources on 4 sites. Artificial Analysis supplies 17 of them; the 8 independently verified results come from 4 sites. Bars are coloured by trust tier.
- artificialanalysis.ai17
- raw.githubusercontent.com4
- aider.chat1
- simple-bench.com1