Enter opens the highlighted result. Esc closes.

Kimi K3 vs MiniMax M3

Kimi K3 leads MiniMax M3 on coding, 62.3 to 39.2 on the Vibe Coding Index, and MiniMax M3 costs 12.5x less per output token ($1.20 vs $15.00 per million). Updated October 22, 2026; 100 benchmarks have a result for both.

Replace Kimi K3 Replace MiniMax M3
Kimi K3Moonshot AI
Coding
62.3
Overall
66.5
Output $/M
$15.00
97
MiniMax M3MiniMax
Coding
39.2
Overall
51.7
Output $/M
$1.20
3
vs boards won of 100 shared

Kimi K3 or MiniMax M3: which to pick

Pick Kimi K3 for coding: it scores 62.3 on the Vibe Coding Index against 39.2 for MiniMax M3.

Pick MiniMax M3 for output tokens 12.5x cheaper ($1.20 vs $15.00 per million) and a lower cost per solved task ($0.56 against $0.81).

Model AKimi K3Moonshot AI62.3/1006 independent benchmarks$0.81 per solved taskModel BMiniMax M3MiniMax39.2/1006 independent benchmarks$0.56 per solved task
Shared results
100
Kimi K3 only
17
MiniMax M3 only
16
Like-for-like categories
8 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 K3 62.3 from 6 benchmarks, MiniMax M3 39.2 from 6 benchmarks.
Widest category
Math, 28.8 points apart on average over 4 shared benchmarks.
Widest single gap
ProofBench: Kimi K3 87.0% against MiniMax M3 18.0%, 69.0 points apart on a 0 to 100 scale.
Output price
Kimi K3 $15.00 against MiniMax M3 $1.20 per million output tokens, 12.5x apart.
Context window
Both take 1.05M tokens.

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 K3BarsMiniMax M3Ties
Coding182
Intelligence20
Agentic work180
Reasoning120
Math40
Knowledge91
Web design80
General260
All shared boards973
CodingLike-for-likeSix of these boards feed the Vibe Coding Index182
Coding benchmarks for Kimi K3 and MiniMax M3
BenchmarkKimi K3MiniMax M3Leader
LiveBench coding59.3%70.9%MiniMax M3
LMArena WebDev16551482Kimi K3
AA Coding Index76.258.6Kimi K3
LiveCodeBench (Vals AI)87.2%82.2%Kimi K3
SWE-bench Verified (Vals AI)93.4%75.0%Kimi K3
Terminal-Bench 4 (Vals AI)17.2%1.0%Kimi K3
Vibe Code Bench (Vals AI)85.0%47.6%Kimi K3
Code migration (Vals AI)16.1%19.9%MiniMax M3
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%53.6%Kimi K3
SWE-bench Multimodal (Vals AI)44.2%33.3%Kimi K3
Vibe Code Bench 1-100 (Vals AI)18.2%9.2%Kimi K3
SkillsBench (Vals AI)Not measured51.5%Only MiniMax M3 measured
CyberBench (Vals AI)75.2%65.0%Kimi K3
SciCode59.5%47.1%Kimi K3
Terminal-Bench Hard (Artificial Analysis run)Not measured42.4%Only MiniMax M3 measured
FrontierCode44.2%14.7%Kimi K3
FrontierSWE25.9%Not measuredOnly Kimi K3 measured
WeirdML82.6%Not measuredOnly Kimi K3 measured
ALE-Bench1524.5640.0Kimi K3
LMArena Text: coding15081470Kimi K3
LMArena Text: software and IT14991466Kimi K3
LMArena WebDev: React16701478Kimi K3
LMArena WebDev: HTML16441455Kimi K3
LMArena WebDev: from an image15791470Kimi K3
Neither model has a result on the other 13 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Kimi K3 and MiniMax M3
BenchmarkKimi K3MiniMax M3Leader
AA Intelligence Index43.629.2Kimi K3
Epoch Capabilities Index157.9146.9Kimi K3
Agentic workLike-for-likePublic boards, shown as published, kept out of the index180
Agentic work benchmarks for Kimi K3 and MiniMax M3
BenchmarkKimi K3MiniMax M3Leader
AA Agentic Index50.029.5Kimi K3
Design Arena: agents building web apps12951200Kimi K3
Design Arena: agents building full-stack apps13151197Kimi K3
Design Arena: agents building mobile apps12691169Kimi K3
Design Arena: agents building Android apps12531159Kimi K3
Design Arena: agents building Godot games1223Not measuredOnly Kimi K3 measured
Design Arena: agents building games12521158Kimi K3
Design Arena: HTML slides12061130Kimi K3
Design Arena: PowerPoint slides12471181Kimi K3
Design Arena: spreadsheets10701028Kimi K3
LiveBench research79.0%68.0%Kimi K3
LiveBench browser16.0%8.0%Kimi K3
LiveBench long agentic42.8%12.4%Kimi K3
Finance Agent (Vals AI)53.1%48.3%Kimi K3
Tax Agent Bench (Vals AI)33.4%20.6%Kimi K3
Legal Research Bench (Vals AI)46.1%29.8%Kimi K3
Harvey's Legal Agent Benchmark (Vals AI)12.9%Not measuredOnly Kimi K3 measured
Excel Modeling Benchmark (Vals AI)66.7%47.8%Kimi K3
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 measured88.9%Only MiniMax M3 measured
APEX-Agents47.8%37.7%Kimi K3
OSWorld 2.0Not measured4.6%Only MiniMax M3 measured
PostTrainBench32.0%Not measuredOnly Kimi K3 measured
Vending-Bench 2$5,165$2,158Kimi K3
Neither model has a result on the other 15 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index120
Reasoning benchmarks for Kimi K3 and MiniMax M3
BenchmarkKimi K3MiniMax M3Leader
GPQA Diamond92.9%92.7%Kimi K3
LiveBench reasoning90.7%74.5%Kimi K3
MMMU Pro (Vals AI)88.2%81.2%Kimi K3
GPQA Diamond (Artificial Analysis run)93.5%92.9%Kimi K3
Humanity's Last Exam (Artificial Analysis run)46.9%39.0%Kimi K3
GPQA Diamond (Epoch AI run)93.1%90.9%Kimi K3
ARC-AGI94.5%Not measuredOnly Kimi K3 measured
ARC-AGI-260.4%Not measuredOnly Kimi K3 measured
SimpleBench60.7%45.8%Kimi K3
Chess puzzles37.0%13.0%Kimi K3
Mystery game puzzles26.0%8.0%Kimi K3
LMArena Text: hard prompts14951447Kimi K3
LMArena Text: expert15201461Kimi K3
LMArena Text: hard prompts in English14961455Kimi K3
LMArena Vision: diagramsNot measured1266Only MiniMax M3 measured
LMArena Vision: homeworkNot measured1268Only MiniMax M3 measured
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index40
Math benchmarks for Kimi K3 and MiniMax M3
BenchmarkKimi K3MiniMax M3Leader
OTIS Mock AIME97.2%71.1%Kimi K3
FrontierMath, tiers 1 to 372.2%Not measuredOnly Kimi K3 measured
FrontierMath, tier 439.0%Not measuredOnly Kimi K3 measured
ProofBench87.0%18.0%Kimi K3
LMArena Text: math14941429Kimi K3
LMArena Text: mathematical work15051448Kimi K3
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index91
Knowledge benchmarks for Kimi K3 and MiniMax M3
BenchmarkKimi K3MiniMax M3Leader
MMLU Pro88.0%84.2%Kimi K3
LegalBench (Vals AI)86.2%85.4%Kimi K3
CorpFin (Vals AI)71.6%68.1%Kimi K3
TaxEval (Vals AI)75.7%72.7%Kimi K3
MortgageTax (Vals AI)66.3%68.4%MiniMax M3
MedCode (Vals AI)49.4%46.3%Kimi K3
SimpleQA Verified50.6%Not measuredOnly Kimi K3 measured
LMArena Text: science15081452Kimi K3
LMArena Text: medicine and healthcare14891441Kimi K3
LMArena Text: legal and government15031437Kimi K3
LMArena Text: business and finance14701434Kimi K3
Neither model has a result on the other 7 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index80
Web design benchmarks for Kimi K3 and MiniMax M3
BenchmarkKimi K3MiniMax M3Leader
Design Arena: websites13341257Kimi K3
Design Arena: UI components13411242Kimi K3
Design Arena: game dev13581210Kimi K3
Design Arena: data viz13511236Kimi K3
Design Arena: 3D13871208Kimi K3
Design Arena: all code categories13601247Kimi K3
Design Arena: SVG13021161Kimi K3
Design Arena: ASCII artNot measured1161Only MiniMax M3 measured
LiveBench design77.2%66.2%Kimi K3
GeneralLike-for-likePublic boards, shown as published, kept out of the index260
General benchmarks for Kimi K3 and MiniMax M3
BenchmarkKimi K3MiniMax M3Leader
Vals Index53.0%Not measuredOnly Kimi K3 measured
LiveBench data analysis78.7%76.2%Kimi K3
Public Benefits Bench (Vals AI)68.2%64.1%Kimi K3
SAGE (Vals AI)52.8%50.6%Kimi K3
MedScribe (Vals AI)88.0%87.3%Kimi K3
Vals Multimodal Index73.4%60.0%Kimi K3
IFBenchNot measured82.9%Only MiniMax M3 measured
Long context reasoning (AA-LCR)88.7%83.0%Kimi K3
DTBench91.2%78.9%Kimi K3
LMCA52.7%33.7%Kimi K3
Surface Evolver Bench95.0%55.0%Kimi K3
Furniture assembly34.2%Not measuredOnly Kimi K3 measured
LMArena Text14761433Kimi K3
LMArena Text: instruction following14851433Kimi K3
LMArena Text: creative writing14571404Kimi K3
LMArena VisionNot measured1251Only MiniMax M3 measured
LMArena Text: English14811443Kimi K3
LMArena Text: non-English14661420Kimi K3
LMArena Text: Chinese15291466Kimi K3
LMArena Text: German14901428Kimi K3
LMArena Text: Japanese14941380Kimi K3
LMArena Text: Korean14601373Kimi K3
LMArena Text: French14921444Kimi K3
LMArena Text: Spanish14721433Kimi K3
LMArena Text: Russian14851426Kimi K3
LMArena Text: Polish14581423Kimi K3
LMArena Text: multi-turn14891443Kimi K3
LMArena Text: longer queries14941446Kimi K3
LMArena Text: writing and language14711419Kimi K3
LMArena Text: entertainment and media14531403Kimi K3
LMArena Vision: EnglishNot measured1263Only MiniMax M3 measured
LMArena Vision: ChineseNot measured1311Only MiniMax M3 measured
LMArena Vision: reading textNot measured1259Only MiniMax M3 measured
LMArena Vision: humorNot measured1235Only MiniMax M3 measured
LMArena Vision: recognizing thingsNot measured1197Only MiniMax M3 measured
LMArena Vision: creative writingNot measured1234Only MiniMax M3 measured
LMArena DocumentNot measured1435Only MiniMax M3 measured
Neither model has a result on the other 9 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Kimi K3 and MiniMax M3
BenchmarkKimi K3MiniMax M3Leader
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$0.011Fits in one request
MiniMax M3$0.0009Fits in one request

MiniMax M3 costs less

Repository review

50K input + 3K output tokens

Kimi K3$0.195Fits in one request
MiniMax M3$0.019Fits in one request

MiniMax M3 costs less

Agent loop

200K input + 10K output tokens

Kimi K3$0.750Fits in one request
MiniMax M3$0.072Fits in one request

MiniMax M3 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 MiniMax M3
SpecificationMoonshotAI Kimi K3MiniMax M3
MakerMoonshot AIMiniMax
WeightsOpen weightsOpen weights
ReleasedJuly 16, 2026May 31, 2026
Context window1.05M1.05M
Input $/Mtok$3.00$0.30
Output $/Mtok$15.00$1.20
Coding index62.339.2
Independent measurements behind it66
Cost per solved task$0.81$0.56
SourceOpenRouter listingOpenRouter listing

Questions

Is Kimi K3 better than MiniMax M3 for coding?

Pick Kimi K3 for coding: it scores 62.3 on the Vibe Coding Index against 39.2 for MiniMax M3. Pick MiniMax M3 for output tokens 12.5x cheaper ($1.20 vs $15.00 per million) and a lower cost per solved task ($0.56 against $0.81).

Which is cheaper, Kimi K3 or MiniMax M3?

Kimi K3 costs $3.00 per million input tokens and $15.00 per million output tokens; MiniMax M3 costs $0.30 and $1.20. Per solved SWE-bench Verified task, Kimi K3 costs $0.81 and MiniMax M3 $0.56.

Which has the bigger context window, Kimi K3 or MiniMax M3?

Neither: both take 1.05M tokens.

How many benchmarks is the Kimi K3 vs MiniMax M3 comparison based on?

100 benchmarks have a result for both models as of October 22, 2026. Kimi K3's coding index rests on 6 independent benchmarks and MiniMax M3's on 6. 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-minimax-minimax-m3" title="Kimi K3 vs MiniMax M3, 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-minimax-minimax-m3">LLMBenchmark.ai, Kimi K3 vs MiniMax M3</a></p>