Enter opens the highlighted result. Esc closes.

Kimi K2.5 vs o1

Kimi K2.5 leads o1 on the Artificial Analysis Intelligence Index, 23.5 to 15.2, and Kimi K2.5 costs 21.1x less per output token ($2.85 vs $60.00 per million). Updated October 22, 2026; 51 benchmarks have a result for both.

Replace Kimi K2.5 Replace o1
Kimi K2.5Moonshot AI
Coding
38.6
Overall
44.8
Output $/M
$2.85
46
o1OpenAI
Coding
No data
Overall
44.6
Output $/M
$60.00
5
vs boards won of 51 shared

Kimi K2.5 or o1: which to pick

Only Kimi K2.5 has a coding score, 38.6 on the Vibe Coding Index; o1 has none, so the two cannot be ranked on coding.

Pick o1 for work measured by WeirdML or TaxEval (Vals AI), where it leads.

Model AKimi K2.5Moonshot AI38.6/1003 independent benchmarks$0.24 per solved taskModel Bo1OpenAINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
51
Kimi K2.5 only
48
o1 only
18
Like-for-like categories
7 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
Kimi K2.5 38.6 from 3 benchmarks, o1 not benchmarked.
Widest category
Agentic work, 33.3 points apart on average over 1 shared benchmark.
Widest single gap
ARC-AGI: Kimi K2.5 65.3% against o1 30.7%, 34.6 points apart on a 0 to 100 scale.
Output price
Kimi K2.5 $2.85 against o1 $60.00 per million output tokens, 21.1x apart.
Context window
Kimi K2.5 takes 262K tokens, o1 200K.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryKimi K2.5Barso1Ties
Coding51
Intelligence20
Agentic work10
Reasoning90
Math30
Knowledge53
General211
All shared boards465
CodingLike-for-likeSix of these boards feed the Vibe Coding Index51
Coding benchmarks for Kimi K2.5 and o1
BenchmarkKimi K2.5o1Leader
Aider polyglotNot measured61.7%Only o1 measured
SWE-bench Verified70.8%Not measuredOnly Kimi K2.5 measured
SWE-bench Multilingual67.3%Not measuredOnly Kimi K2.5 measured
LMArena WebDev1437Not measuredOnly Kimi K2.5 measured
AA Coding Index46.839.7Kimi K2.5
LiveCodeBench (Vals AI)83.9%50.3%Kimi K2.5
SWE-bench Verified (Vals AI)70.0%Not measuredOnly Kimi K2.5 measured
Vibe Code Bench (Vals AI)17.5%Not measuredOnly Kimi K2.5 measured
Code migration (Vals AI)7.0%Not measuredOnly Kimi K2.5 measured
Terminal-Bench 2.1 (Vals AI)42.0%Not measuredOnly Kimi K2.5 measured
LiveCodeBench (Artificial Analysis run)Not measured67.9%Only o1 measured
Terminal-Bench Hard (Artificial Analysis run)34.8%12.9%Kimi K2.5
Terminal-Bench43.2%Not measuredOnly Kimi K2.5 measured
WeirdML45.6%46.1%o1
ALE-Bench821.6Not measuredOnly Kimi K2.5 measured
LMArena Text: coding14831367Kimi K2.5
LMArena Text: software and IT14711366Kimi K2.5
LMArena WebDev: React1429Not measuredOnly Kimi K2.5 measured
LMArena WebDev: HTML1426Not measuredOnly Kimi K2.5 measured
LMArena WebDev: from an image1439Not measuredOnly Kimi K2.5 measured
SciCodeNot measured4.6%Only o1 measured
Neither model has a result on the other 18 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Kimi K2.5 and o1
BenchmarkKimi K2.5o1Leader
AA Intelligence Index23.515.2Kimi K2.5
Epoch Capabilities Index148.1141.7Kimi K2.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for Kimi K2.5 and o1
BenchmarkKimi K2.5o1Leader
Design Arena: agents building web apps1136Not measuredOnly Kimi K2.5 measured
Design Arena: agents building full-stack apps1114Not measuredOnly Kimi K2.5 measured
Design Arena: agents building mobile apps1147Not measuredOnly Kimi K2.5 measured
Design Arena: agents building Android apps1118Not measuredOnly Kimi K2.5 measured
Design Arena: agents building Godot games1219Not measuredOnly Kimi K2.5 measured
Finance Agent (Vals AI)35.8%Not measuredOnly Kimi K2.5 measured
Legal Research Bench (Vals AI)15.9%Not measuredOnly Kimi K2.5 measured
Excel Modeling Benchmark (Vals AI)28.5%Not measuredOnly Kimi K2.5 measured
τ²-Bench Telecom95.9%62.6%Kimi K2.5
METR time horizonsNot measured51.1%Only o1 measured
OSWorld63.3%Not measuredOnly Kimi K2.5 measured
Vending-Bench 2$1,198Not measuredOnly Kimi K2.5 measured
Neither model has a result on the other 29 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index90
Reasoning benchmarks for Kimi K2.5 and o1
BenchmarkKimi K2.5o1Leader
GPQA Diamond84.1%73.2%Kimi K2.5
MMMU Pro (Vals AI)84.3%77.4%Kimi K2.5
GPQA Diamond (Artificial Analysis run)87.9%74.7%Kimi K2.5
Humanity's Last Exam (Artificial Analysis run)30.7%7.0%Kimi K2.5
GPQA Diamond (Epoch AI run)Not measured76.8%Only o1 measured
ARC-AGI65.3%30.7%Kimi K2.5
ARC-AGI-211.8%Not measuredOnly Kimi K2.5 measured
SimpleBench46.8%40.1%Kimi K2.5
Chess puzzlesNot measured10.0%Only o1 measured
VPCTNot measured37.0%Only o1 measured
LMArena Text: hard prompts14531371Kimi K2.5
LMArena Text: expert14661361Kimi K2.5
LMArena Text: hard prompts in English14601372Kimi K2.5
LMArena Vision: diagrams1282Not measuredOnly Kimi K2.5 measured
LMArena Vision: homework1297Not measuredOnly Kimi K2.5 measured
Kagi LLM Benchmark78.5%Not measuredOnly Kimi K2.5 measured
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index30
Math benchmarks for Kimi K2.5 and o1
BenchmarkKimi K2.5o1Leader
AIME95.6%71.5%Kimi K2.5
MATH 500 (Vals AI)Not measured90.4%Only o1 measured
MGSM (Vals AI)Not measured89.3%Only o1 measured
OTIS Mock AIMENot measured73.3%Only o1 measured
FrontierMath, tiers 1 to 3Not measured14.7%Only o1 measured
MATH level 5Not measured94.7%Only o1 measured
LMArena Text: math14701388Kimi K2.5
LMArena Text: mathematical work14731390Kimi K2.5
Neither model has a result on the other 5 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index53
Knowledge benchmarks for Kimi K2.5 and o1
BenchmarkKimi K2.5o1Leader
MMLU Pro85.9%83.5%Kimi K2.5
LegalBench (Vals AI)Not measured80.4%Only o1 measured
CaseLaw (Vals AI)58.7%Not measuredOnly Kimi K2.5 measured
CorpFin (Vals AI)68.3%Not measuredOnly Kimi K2.5 measured
TaxEval (Vals AI)74.2%74.3%o1
MortgageTax (Vals AI)66.5%Not measuredOnly Kimi K2.5 measured
MedQA (Vals AI)94.4%96.5%o1
MedCode (Vals AI)39.3%Not measuredOnly Kimi K2.5 measured
MMLU Pro (Artificial Analysis run)Not measured84.1%Only o1 measured
SimpleQA Verified34.3%41.1%o1
GeoBenchNot measured80.0%Only o1 measured
LMArena Text: science14591369Kimi K2.5
LMArena Text: medicine and healthcare14481355Kimi K2.5
LMArena Text: legal and government14411368Kimi K2.5
LMArena Text: business and finance14271328Kimi K2.5
Neither model has a result on the other 3 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for Kimi K2.5 and o1
BenchmarkKimi K2.5o1Leader
Design Arena: websites1248Not measuredOnly Kimi K2.5 measured
Design Arena: UI components1234Not measuredOnly Kimi K2.5 measured
Design Arena: game dev1206Not measuredOnly Kimi K2.5 measured
Design Arena: data viz1219Not measuredOnly Kimi K2.5 measured
Design Arena: 3D1204Not measuredOnly Kimi K2.5 measured
Design Arena: all code categories1236Not measuredOnly Kimi K2.5 measured
Design Arena: SVG1149Not measuredOnly Kimi K2.5 measured
Design Arena: ASCII art1166Not measuredOnly Kimi K2.5 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index211
General benchmarks for Kimi K2.5 and o1
BenchmarkKimi K2.5o1Leader
SAGE (Vals AI)49.9%Not measuredOnly Kimi K2.5 measured
MedScribe (Vals AI)76.4%Not measuredOnly Kimi K2.5 measured
IFBench70.2%70.3%o1
Long context reasoning (AA-LCR)78.0%65.0%Kimi K2.5
DTBenchNot measured74.7%Only o1 measured
LMCANot measured22.3%Only o1 measured
Fiction.LiveBench86.1%83.3%Kimi K2.5
Creative writing (Lech Mazur)Not measured70.2%Only o1 measured
CL-bench19.3%Not measuredOnly Kimi K2.5 measured
CL-bench Life13.2%Not measuredOnly Kimi K2.5 measured
LMArena Text14451366Kimi K2.5
LMArena Text: instruction following14311367Kimi K2.5
LMArena Text: creative writing14221347Kimi K2.5
LMArena Vision12691168Kimi K2.5
LMArena Text: English14531372Kimi K2.5
LMArena Text: non-English14331358Kimi K2.5
LMArena Text: Chinese14941394Kimi K2.5
LMArena Text: German14411337Kimi K2.5
LMArena Text: Japanese14231346Kimi K2.5
LMArena Text: Korean14121396Kimi K2.5
LMArena Text: French14541344Kimi K2.5
LMArena Text: Spanish14501345Kimi K2.5
LMArena Text: Russian14351356Kimi K2.5
LMArena Text: Polish1445Not measuredOnly Kimi K2.5 measured
LMArena Text: multi-turn14441355Kimi K2.5
LMArena Text: longer queries14451378Kimi K2.5
LMArena Text: writing and language14251360Kimi K2.5
LMArena Text: entertainment and media14171358Kimi K2.5
LMArena Vision: English12741162Kimi K2.5
LMArena Vision: Chinese13281235Kimi K2.5
LMArena Vision: reading text1276Not measuredOnly Kimi K2.5 measured
LMArena Vision: humor1284Not measuredOnly Kimi K2.5 measured
LMArena Vision: captioning1257Not measuredOnly Kimi K2.5 measured
LMArena Vision: recognizing things1285Not measuredOnly Kimi K2.5 measured
LMArena Vision: creative writing1269Not measuredOnly Kimi K2.5 measured
Neither model has a result on the other 11 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Kimi K2.5 and o1
BenchmarkKimi K2.5o1Leader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

Kimi K2.5$0.0020Fits in one request
o1$0.045Fits in one request

Kimi K2.5 costs less

Repository review

50K input + 3K output tokens

Kimi K2.5$0.035Fits in one request
o1$0.930Fits in one request

Kimi K2.5 costs less

Agent loop

200K input + 10K output tokens

Kimi K2.5$0.135Fits in one request
o1$3.60Exceeds the context window

Kimi K2.5 costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of Kimi K2.5 and o1
SpecificationMoonshotAI Kimi K2.5OpenAI o1
MakerMoonshot AIOpenAI
WeightsOpen weightsNo public weights listed
ReleasedJanuary 27, 2026December 17, 2024
Context window262K200K
Input $/Mtok$0.532$15.00
Output $/Mtok$2.85$60.00
Coding index38.6Not benchmarked
Independent measurements behind it30
Cost per solved task$0.24Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Kimi K2.5 better than o1 for coding?

Only Kimi K2.5 has a coding score, 38.6 on the Vibe Coding Index; o1 has none, so the two cannot be ranked on coding. Pick o1 for work measured by WeirdML or TaxEval (Vals AI), where it leads.

Which is cheaper, Kimi K2.5 or o1?

Kimi K2.5 costs $0.532 per million input tokens and $2.85 per million output tokens; o1 costs $15.00 and $60.00. Cost per solved task is known for Kimi K2.5 only.

Which has the bigger context window, Kimi K2.5 or o1?

Kimi K2.5, with 262K tokens against 200K.

How many benchmarks is the Kimi K2.5 vs o1 comparison based on?

51 benchmarks have a result for both models as of October 22, 2026. Kimi K2.5's coding index rests on 3 independent benchmarks and o1's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next