Kimi K2.5
Made by Moonshot, released 27 Jan 2026. Epoch AI lists its access as “Open weights (unrestricted)”. No Top tier or Strong results yet among the models listed here.
In short
What it does well
No Top tier or Strong ratings on the four main tests yet.
Where it falls short
- Knowledge: Behind the leaders (35th of 43 listed models)
- Coding: Middle (47th of 77 listed models)
- Writing: Middle (55th of 77 listed models)
What we don't know yet
- Hard maths problems: Not enough data
- School-competition maths: Not enough data
- Graduate-level science questions: Not enough data
- Difficult coding tasks: Not enough data
The four ratings
- Top tier
- Strong
- Middle
- Behind the leaders
- Not enough data
Ratings compare only the 77 models listed here, in quarters, best first. “Not enough data” means no result yet. It is never a low score.
- Writing
- MiddleHow often people preferred its answers to writing prompts. 1,422 on Arena's scale · Source for Kimi K2.5 writing score (lmarena)
- Coding
- MiddleHow often people preferred its answers to coding questions. 1,474 on Arena's scale · Source for Kimi K2.5 coding score (lmarena)
- Maths
- Not enough dataNo result yet for hard maths problems.
- Knowledge
- Behind the leadersHow many short factual questions it answered correctly. 34.3% · Source for Kimi K2.5 knowledge score (epoch)
Evidence completeness: Partial evidence, 9 of 13 tests have a result.
Where it is relatively stronger or weaker
This compares each kind of request with the model's own overall position among the 77 listed models, using Arena's votes. It is about performance on different languages, kinds of request and topics, not about political or social bias.
Relatively stronger
No category stands out as clearly stronger than its overall position.
Relatively weaker
No category stands out as clearly weaker than its overall position.
Show every category we can see
| Category | Position | Arena score | Votes | Source |
|---|---|---|---|---|
| Expert-level prompts Kind of request | 50th of 77 | 1,466 95% range 1,458 to 1,474 | 7,024 | Source for Expert-level prompts |
| Hard prompts Kind of request | 53rd of 77 | 1,453 95% range 1,449 to 1,457 | 47,876 | Source for Hard prompts |
| Long prompts Kind of request | 56th of 77 | 1,444 95% range 1,440 to 1,449 | 29,795 | Source for Long prompts |
| Longer conversations Kind of request | 59th of 77 | 1,444 95% range 1,438 to 1,450 | 13,138 | Source for Longer conversations |
| Chinese Language | 47th of 76 | 1,494 95% range 1,485 to 1,503 | 4,587 | Source for Chinese |
| English prompts Language | 50th of 77 | 1,453 95% range 1,449 to 1,458 | 31,747 | Source for English prompts |
| French Language | 57th of 72 | 1,453 95% range 1,440 to 1,466 | 2,624 | Source for French |
| German Language | 44th of 55 | 1,441 95% range 1,424 to 1,459 | 1,291 | Source for German |
| Japanese Language | 33rd of 54 | 1,422 95% range 1,400 to 1,443 | 851 | Source for Japanese |
| Korean Language | 38th of 54 | 1,412 95% range 1,395 to 1,429 | 1,361 | Source for Korean |
| Non-English prompts Language | 53rd of 77 | 1,432 95% range 1,428 to 1,436 | 42,932 | Source for Non-English prompts |
| Russian Language | 60th of 77 | 1,435 95% range 1,428 to 1,442 | 8,814 | Source for Russian |
| Spanish Language | 44th of 70 | 1,450 95% range 1,437 to 1,462 | 2,533 | Source for Spanish |
| Entertainment, sport and media Topic | 55th of 77 | 1,417 95% range 1,411 to 1,422 | 15,488 | Source for Entertainment, sport and media |
| Law and government Topic | 61st of 76 | 1,441 95% range 1,432 to 1,449 | 5,644 | Source for Law and government |
| Medicine and health Topic | 53rd of 75 | 1,448 95% range 1,439 to 1,457 | 5,162 | Source for Medicine and health |
| Science Topic | 50th of 77 | 1,459 95% range 1,453 to 1,465 | 11,809 | Source for Science |
| Software and IT Topic | 49th of 77 | 1,469 95% range 1,464 to 1,473 | 29,757 | Source for Software and IT |
Bias: what we can and can't see
Our sources do not measure political lean, stereotyping, flattery (agreeing with you too readily) or safety behaviour, so we cannot say how any model does on those. What we can show is above: where a model is relatively stronger or weaker across languages, kinds of request and topics. Also, people voting in Arena can favour answer style, such as length and formatting, and our numbers do not adjust for that. See what AI bias means and what these tests can tell you.
Best-supported use cases
- Homework and maths: not ranked, because there is not enough data for the main test.
Where an alternative might be more suitable
- Writing and creating content: rated Middle on writing votes. Compare it with Claude Opus 5.5, the best-supported choice for this task.
- Coding and building things: rated Middle on coding votes. Compare it with Claude Opus 5.5, the best-supported choice for this task.
- Homework and maths: no result on hard maths problems, so we cannot say. See which models the evidence does support.
- Business emails and everyday work: rated Behind the leaders on business-task votes. Compare it with Gemini 4 Argon, the best-supported choice for this task.
- Research and checking facts: rated Behind the leaders on short factual questions. Compare it with Gemini 4 Argon, the best-supported choice for this task.
What it is
- Maker
- Moonshot
- Release date (Epoch AI)
- 27 Jan 2026
- Access, as listed by Epoch AI
- Open weights (unrestricted)
- Licence, as listed by Arena
- Modified MIT
- Maker's country (Epoch AI)
- China
- Last observation in our data
- 28 Oct 2026
- Data last changed
- 29 Oct 2026, 14:36 UTC
We have not verified an official product page for this model, so we do not link to one.
How you can use it
Open weights. Arena lists its licence as Modified MIT. In plain terms, the model's files are published under a licence that lets others run it, so it can be offered by more than one company, sometimes at lower cost. That does not guarantee that any particular app is free. Open licences differ, and some restrict commercial use, so check the licence terms before building a business on it.
How you can reach it (an app, a website, a developer API or a third-party tool) and what that costs are not covered by our benchmark data. Where we could verify prices from the maker's own pages, they are shown under Price. Epoch AI lists access as “Open weights (unrestricted)”. See models, apps and harnesses and how AI pricing works.
Price
Price not independently verified
We have not been able to check this maker's own pricing page, so we show nothing for it.
We never infer subscription prices from API prices. New to “tokens” and “per million”? See how AI pricing works.
Good to remember
- Benchmarks are samples of tasks. None proves performance in every situation.
- Arena scores come from people choosing between answers. That measures preference, not correctness.
- Ratings are relative to the 77 models listed here. A different set would change them.
- Sources test models at different settings. Each result shows the setting used, and we do not adjust it.
The evidence, for the curious
Show all 13 tests with settings and sources
| Test | Result | Rating | Setting used | Source identifier | Observed | Links |
|---|---|---|---|---|---|---|
| Arena text: overall preference Arena 'text' leaderboard (Bradley-Terry rating, no style control) |
1,445 Arena score 95% range 1,442 to 1,448, 74,682 votes |
Middle | effort: Thinking, bradley-terry rating | Kimi K2.5 (Thinking) lmarena · text/latest |
28 Oct 2026 | Source for Kimi K2.5 Arena text: overall preference score (lmarena) |
| Arena text: creative writing Arena 'text' leaderboard, category creative_writing |
1,422 Arena score 95% range 1,416 to 1,428, 12,231 votes |
Middle | effort: Thinking, bradley-terry rating | Kimi K2.5 (Thinking) lmarena · text/latest |
28 Oct 2026 | Source for Kimi K2.5 Arena text: creative writing score (lmarena) |
| Arena text: coding Arena 'text' leaderboard, category coding |
1,474 Arena score 95% range 1,469 to 1,479, 20,752 votes |
Middle | effort: Thinking, bradley-terry rating | Kimi K2.5 (Thinking) lmarena · text/latest |
28 Oct 2026 | Source for Kimi K2.5 Arena text: coding score (lmarena) |
| Arena text: maths Arena 'text' leaderboard, category math |
1,470 Arena score 95% range 1,461 to 1,479, 4,171 votes |
Strong | effort: Thinking, bradley-terry rating | Kimi K2.5 (Thinking) lmarena · text/latest |
28 Oct 2026 | Source for Kimi K2.5 Arena text: maths score (lmarena) |
| Arena text: following instructions Arena 'text' leaderboard, category instruction_following |
1,431 Arena score 95% range 1,426 to 1,436, 24,181 votes |
Middle | effort: Thinking, bradley-terry rating | Kimi K2.5 (Thinking) lmarena · text/latest |
28 Oct 2026 | Source for Kimi K2.5 Arena text: following instructions score (lmarena) |
| Arena text: business and management Arena 'text' leaderboard, category industry_business_and_management_and_financial_operations |
1,427 Arena score 95% range 1,421 to 1,432, 14,392 votes |
Behind the leaders | effort: Thinking, bradley-terry rating | Kimi K2.5 (Thinking) lmarena · text/latest |
28 Oct 2026 | Source for Kimi K2.5 Arena text: business and management score (lmarena) |
| Arena WebDev: building web apps Arena 'webdev' leaderboard (Code Arena), category overall |
1,436 Arena score 95% range 1,431 to 1,441, 20,008 votes |
Behind the leaders | effort: Thinking, bradley-terry rating | Kimi K2.5 (Thinking) lmarena · webdev/latest |
28 Oct 2026 | Source for Kimi K2.5 Arena WebDev: building web apps score (lmarena) |
| FrontierMath Tiers 1-3 (v2) | Not enough data | |||||
| OTIS Mock AIME 2024-2025 | Not enough data | |||||
| GPQA Diamond | Not enough data | |||||
| SimpleQA Verified SimpleQA Verified, benchmark released 2025-09-09 |
34.3% share of questions correct standard error ±1.5 points |
Behind the leaders | effort: not stated, best score across scorers | kimi-k2.5 epoch · simpleqa_verified.csv |
27 Aug 2026 | Source for Kimi K2.5 SimpleQA Verified score (epoch) · Run details for SimpleQA Verified |
| SWE-bench Verified (Epoch runs) SWE-bench Verified, benchmark released 2024-08-13, as run by Epoch AI |
73.8% share of issues resolved standard error ±2.0 points |
Middle | effort: not stated, best score across scorers | kimi-k2.5 epoch · swe_bench_verified.csv |
17 Feb 2026 | Source for Kimi K2.5 SWE-bench Verified (Epoch runs) score (epoch) · Run details for SWE-bench Verified (Epoch runs) |
| FrontierCode (reported by Cognition) | Not enough data | |||||
Missing evidence
Not enough data for these tests:
- FrontierMath Tiers 1-3 (v2)
- OTIS Mock AIME 2024-2025
- GPQA Diamond
- FrontierCode (reported by Cognition)
Missing results are not low scores and do not count against the model.
Where a source gives no public run log, we cannot show the run behind the score. See data sources.
Not sure this is the right one?
Tell us what you need help with and we'll narrow the options down.