LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Kimi K3 vs o4 Mini

Updated October 21, 2026. 63 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Kimi K3 Replace o4 Mini
Kimi K3Moonshot AI
Coding
61.8
Overall
43.6
Output $/M
$11.936
63
o4 MiniOpenAI
Coding
68.6
Overall
16.7
Output $/M
$4.40
0
vs boards won of 63 shared

Decision reading

Pick o4 Mini for coding: it scores 68.6 on the Vibe Coding Index against 61.8 for Kimi K3.

Pick Kimi K3 when the context window is larger, 1.05M against 200K tokens, or when what matters is LiveCodeBench (Vals AI) or WeirdML, where it leads.

Model AKimi K3Moonshot AI61.8/1002 independent benchmarks$0.81 per solved taskModel Bo4 MiniOpenAI68.6/1002 independent benchmarksNo cost per solved task
Shared results
63
Kimi K3 only
54
o4 Mini only
31
Like-for-like categories
7 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

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 K3 61.8 from 2 benchmarks, o4 Mini 68.6 from 2 benchmarks.
Widest category
Web design, 48.9 points apart on average over 6 shared benchmarks.
Widest single gap
Design Arena: 3D: Kimi K3 1388 against o4 Mini 854, 66.8 points apart on a 0 to 100 scale.
Output price
Kimi K3 $11.936 against o4 Mini $4.40 per million output tokens, 2.7x apart.
Context window
Kimi K3 takes 1.05M tokens, o4 Mini 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 K3Barso4 MiniTies
Coding40
Intelligence20
Reasoning130
Math50
Knowledge110
Web design60
General220
All shared boards630
CodingLike-for-likeFour of these boards feed the Vibe Coding Index40
Coding benchmarks for Kimi K3 and o4 Mini
BenchmarkKimi K3o4 MiniLeader
Aider polyglotNot measured72.0%Only o4 Mini measured
SWE-bench VerifiedNot measured64.6%Only o4 Mini measured
SWE-bench MultimodalNot measured33.9%Only o4 Mini measured
LiveBench coding59.3%Not measuredOnly Kimi K3 measured
LMArena WebDev1655Not measuredOnly Kimi K3 measured
AA Coding Index76.2Not measuredOnly Kimi K3 measured
LiveCodeBench (Vals AI)87.2%82.2%Kimi K3
SWE-bench Verified (Vals AI)93.4%Not measuredOnly Kimi K3 measured
Terminal-Bench 4 (Vals AI)17.2%Not measuredOnly Kimi K3 measured
Vibe Code Bench (Vals AI)85.0%Not measuredOnly Kimi K3 measured
Code migration (Vals AI)16.1%Not measuredOnly Kimi K3 measured
ProgramBench (Vals AI)2.0%Not measuredOnly Kimi K3 measured
IOI (Vals AI)48.9%Not measuredOnly Kimi K3 measured
Terminal-Bench 2.1 (Vals AI)80.9%Not measuredOnly Kimi K3 measured
SWE-bench Multimodal (Vals AI)44.2%Not measuredOnly Kimi K3 measured
Vibe Code Bench 1-100 (Vals AI)18.2%Not measuredOnly Kimi K3 measured
CyberBench (Vals AI)75.2%Not measuredOnly Kimi K3 measured
LiveCodeBench (Artificial Analysis run)Not measured85.9%Only o4 Mini measured
SciCode59.5%Not measuredOnly Kimi K3 measured
Terminal-Bench Hard (Artificial Analysis run)Not measured15.2%Only o4 Mini measured
FrontierCode44.2%Not measuredOnly Kimi K3 measured
FrontierSWE25.9%Not measuredOnly Kimi K3 measured
GSO-BenchNot measured3.6%Only o4 Mini measured
WeirdML82.6%52.6%Kimi K3
ALE-Bench1524.5Not measuredOnly Kimi K3 measured
LMArena Text: coding15081368Kimi K3
LMArena Text: software and IT14991367Kimi K3
LMArena WebDev: React1670Not measuredOnly Kimi K3 measured
LMArena WebDev: HTML1644Not measuredOnly Kimi K3 measured
LMArena WebDev: from an image1579Not measuredOnly Kimi K3 measured
Neither model has a result on the other 8 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Kimi K3 and o4 Mini
BenchmarkKimi K3o4 MiniLeader
AA Intelligence Index43.616.7Kimi K3
Epoch Capabilities Index157.9145.5Kimi K3
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index26 boards, none shared
Agentic work benchmarks for Kimi K3 and o4 Mini
BenchmarkKimi K3o4 MiniLeader
AA Agentic Index50.0Not measuredOnly Kimi K3 measured
Design Arena: agents building web apps1296Not measuredOnly Kimi K3 measured
Design Arena: agents building full-stack apps1315Not measuredOnly Kimi K3 measured
Design Arena: agents building mobile apps1267Not measuredOnly Kimi K3 measured
Design Arena: agents building Android apps1256Not measuredOnly Kimi K3 measured
Design Arena: agents building Godot games1223Not measuredOnly Kimi K3 measured
Design Arena: agents building games1252Not measuredOnly Kimi K3 measured
Design Arena: HTML slides1256Not measuredOnly Kimi K3 measured
Design Arena: PowerPoint slides1273Not measuredOnly Kimi K3 measured
Design Arena: spreadsheets1058Not measuredOnly Kimi K3 measured
LiveBench research79.0%Not measuredOnly Kimi K3 measured
LiveBench browser16.0%Not measuredOnly Kimi K3 measured
LiveBench long agentic42.8%Not measuredOnly Kimi K3 measured
Finance Agent (Vals AI)53.1%Not measuredOnly Kimi K3 measured
Tax Agent Bench (Vals AI)33.4%Not measuredOnly Kimi K3 measured
Legal Research Bench (Vals AI)46.1%Not measuredOnly Kimi K3 measured
Harvey's Legal Agent Benchmark (Vals AI)12.9%Not measuredOnly Kimi K3 measured
Excel Modeling Benchmark (Vals AI)66.7%Not measuredOnly Kimi K3 measured
BioMysteryBench (Vals AI)72.6%Not measuredOnly Kimi K3 measured
Terminal-Bench-Science (Vals AI)1.4%Not measuredOnly Kimi K3 measured
Time Horizon Index (Vals AI)10.5%Not measuredOnly Kimi K3 measured
τ²-Bench TelecomNot measured55.6%Only o4 Mini measured
APEX-Agents47.8%Not measuredOnly Kimi K3 measured
METR time horizonsNot measured63.9%Only o4 Mini measured
PostTrainBench32.0%Not measuredOnly Kimi K3 measured
Vending-Bench 2$5,165Not measuredOnly Kimi K3 measured
Neither model has a result on the other 13 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index130
Reasoning benchmarks for Kimi K3 and o4 Mini
BenchmarkKimi K3o4 MiniLeader
GPQA Diamond92.9%74.5%Kimi K3
LiveBench reasoning90.7%Not measuredOnly Kimi K3 measured
MMMU Pro (Vals AI)88.2%79.7%Kimi K3
GPQA Diamond (Artificial Analysis run)93.5%78.4%Kimi K3
Humanity's Last Exam (Artificial Analysis run)46.9%16.5%Kimi K3
GPQA Diamond (Epoch AI run)93.1%79.6%Kimi K3
ARC-AGI94.5%58.7%Kimi K3
ARC-AGI-260.4%6.1%Kimi K3
SimpleBench60.7%38.7%Kimi K3
Chess puzzles37.0%22.0%Kimi K3
Mystery game puzzles26.0%5.0%Kimi K3
VPCTNot measured57.5%Only o4 Mini measured
LMArena Text: hard prompts14951351Kimi K3
LMArena Text: expert15201343Kimi K3
LMArena Text: hard prompts in English14961366Kimi K3
LMArena Vision: diagramsNot measured1197Only o4 Mini measured
LMArena Vision: homeworkNot measured1234Only o4 Mini measured
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index50
Math benchmarks for Kimi K3 and o4 Mini
BenchmarkKimi K3o4 MiniLeader
AIMENot measured83.7%Only o4 Mini measured
MATH 500 (Vals AI)Not measured94.2%Only o4 Mini measured
MGSM (Vals AI)Not measured93.4%Only o4 Mini measured
AA Math IndexNot measured90.7Only o4 Mini measured
AIME 2025 (Artificial Analysis run)Not measured90.7%Only o4 Mini measured
OTIS Mock AIME97.2%81.7%Kimi K3
FrontierMath, tiers 1 to 372.2%36.1%Kimi K3
FrontierMath, tier 439.0%4.9%Kimi K3
ProofBench87.0%Not measuredOnly Kimi K3 measured
MATH level 5Not measured97.8%Only o4 Mini measured
LMArena Text: math14941389Kimi K3
LMArena Text: mathematical work15051379Kimi K3
Neither model has a result on the other 1 board here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index110
Knowledge benchmarks for Kimi K3 and o4 Mini
BenchmarkKimi K3o4 MiniLeader
MMLU Pro88.0%80.6%Kimi K3
LegalBench (Vals AI)86.2%79.2%Kimi K3
CorpFin (Vals AI)71.6%59.0%Kimi K3
TaxEval (Vals AI)75.7%74.8%Kimi K3
MortgageTax (Vals AI)66.3%64.8%Kimi K3
MedQA (Vals AI)Not measured96.0%Only o4 Mini measured
MedCode (Vals AI)49.4%33.8%Kimi K3
MMLU Pro (Artificial Analysis run)Not measured83.2%Only o4 Mini measured
SimpleQA Verified50.6%19.6%Kimi K3
GeoBenchNot measured64.0%Only o4 Mini measured
LMArena Text: science15081354Kimi K3
LMArena Text: medicine and healthcare14891361Kimi K3
LMArena Text: legal and government15031350Kimi K3
LMArena Text: business and finance14701325Kimi K3
Neither model has a result on the other 3 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index60
Web design benchmarks for Kimi K3 and o4 Mini
BenchmarkKimi K3o4 MiniLeader
Design Arena: websites1336985Kimi K3
Design Arena: UI components1345983Kimi K3
Design Arena: game dev13611004Kimi K3
Design Arena: data viz1350990Kimi K3
Design Arena: 3D1388854Kimi K3
Design Arena: all code categories1361977Kimi K3
Design Arena: SVG1301Not measuredOnly Kimi K3 measured
LiveBench design77.2%Not measuredOnly Kimi K3 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index220
General benchmarks for Kimi K3 and o4 Mini
BenchmarkKimi K3o4 MiniLeader
Vals Index53.0%Not measuredOnly Kimi K3 measured
LiveBench data analysis78.7%Not measuredOnly Kimi K3 measured
Public Benefits Bench (Vals AI)68.2%Not measuredOnly Kimi K3 measured
SAGE (Vals AI)52.8%41.1%Kimi K3
MedScribe (Vals AI)88.0%69.1%Kimi K3
Vals Multimodal Index73.4%Not measuredOnly Kimi K3 measured
IFBenchNot measured68.7%Only o4 Mini measured
Long context reasoning (AA-LCR)88.7%61.0%Kimi K3
DTBench91.2%77.6%Kimi K3
LMCA52.7%26.5%Kimi K3
Fiction.LiveBenchNot measured77.8%Only o4 Mini measured
Creative writing (Lech Mazur)Not measured75.0%Only o4 Mini measured
Surface Evolver Bench95.0%Not measuredOnly Kimi K3 measured
Furniture assembly34.2%Not measuredOnly Kimi K3 measured
LMArena Text14761353Kimi K3
LMArena Text: instruction following14851320Kimi K3
LMArena Text: creative writing14571294Kimi K3
LMArena VisionNot measured1194Only o4 Mini measured
LMArena Text: English14811367Kimi K3
LMArena Text: non-English14661337Kimi K3
LMArena Text: Chinese15291354Kimi K3
LMArena Text: German14901336Kimi K3
LMArena Text: Japanese14941308Kimi K3
LMArena Text: Korean14601312Kimi K3
LMArena Text: French14921364Kimi K3
LMArena Text: Spanish14721346Kimi K3
LMArena Text: Russian14851334Kimi K3
LMArena Text: Polish14581358Kimi K3
LMArena Text: multi-turn14891350Kimi K3
LMArena Text: longer queries14941315Kimi K3
LMArena Text: writing and language14711316Kimi K3
LMArena Text: entertainment and media14531308Kimi K3
LMArena Vision: EnglishNot measured1200Only o4 Mini measured
LMArena Vision: ChineseNot measured1218Only o4 Mini measured
LMArena Vision: reading textNot measured1197Only o4 Mini measured
LMArena Vision: humorNot measured1199Only o4 Mini measured
LMArena Vision: captioningNot measured1204Only o4 Mini measured
LMArena Vision: recognizing thingsNot measured1218Only o4 Mini measured
LMArena Vision: creative writingNot measured1166Only o4 Mini measured
Neither model has a result on the other 7 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Kimi K3 and o4 Mini
BenchmarkKimi K3o4 MiniLeader
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 K3$0.0062Fits in one request
o4 Mini$0.0033Fits in one request

o4 Mini costs less

Repository review

50K input + 3K output tokens

Kimi K3$0.048Fits in one request
o4 Mini$0.068Fits in one request

Kimi K3 costs less

Agent loop

200K input + 10K output tokens

Kimi K3$0.167Fits in one request
o4 Mini$0.264Exceeds the context window

Kimi K3 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 K3 and o4 Mini
SpecificationMoonshotAI Kimi K3OpenAI o4 Mini
MakerMoonshot AIOpenAI
WeightsOpen weightsNo public weights listed
ReleasedJuly 16, 2026April 16, 2025
Context window1.05M200K
Input $/Mtok$0.239$1.10
Output $/Mtok$11.936$4.40
Coding index61.868.6
Independent measurements behind it22
Cost per solved task$0.81Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Kimi K3 better than o4 Mini for coding?

Pick o4 Mini for coding: it scores 68.6 on the Vibe Coding Index against 61.8 for Kimi K3. Pick Kimi K3 when the context window is larger, 1.05M against 200K tokens, or when what matters is LiveCodeBench (Vals AI) or WeirdML, where it leads.

Which is cheaper, Kimi K3 or o4 Mini?

Kimi K3 costs $0.239 per million input tokens and $11.936 per million output tokens; o4 Mini costs $1.10 and $4.40. Cost per solved task is known for Kimi K3 only.

Which has the bigger context window, Kimi K3 or o4 Mini?

Kimi K3, with 1.05M tokens against 200K.

How many benchmarks is the Kimi K3 vs o4 Mini comparison based on?

63 benchmarks have a result for both models as of October 21, 2026. Kimi K3's coding index rests on 2 independent benchmarks and o4 Mini's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next

Embed this comparison on your site

Free under CC BY 4.0, while the source link stays visible. Preview the frame · Terms and other embeds

<iframe src="https://llmbenchmark.ai/embed/compare/kimi-k3-vs-o4-mini" title="Kimi K3 vs o4 Mini, LLMBenchmark.ai" width="100%" height="360" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/compare/kimi-k3-vs-o4-mini">LLMBenchmark.ai, Kimi K3 vs o4 Mini</a></p>