Enter opens the highlighted result. Esc closes.

Kimi K3 vs Mistral Large 4

Kimi K3 leads Mistral Large 4 on coding, 62.3 to 56.4 on the Vibe Coding Index, and Mistral Large 4 costs 3.6x less per output token ($4.18 vs $15.00 per million). Updated October 22, 2026; 75 benchmarks have a result for both.

Replace Kimi K3 Replace Mistral Large 4
Kimi K3Moonshot AI
Coding
62.3
Overall
66.5
Output $/M
$15.00
68
Mistral Large 4Mistral AI
Coding
56.4
Overall
54.6
Output $/M
$4.18
7
vs boards won of 75 shared

Kimi K3 or Mistral Large 4: which to pick

Pick Kimi K3 for coding: it scores 62.3 on the Vibe Coding Index against 56.4 for Mistral Large 4.

Pick Mistral Large 4 for output tokens 3.6x cheaper ($4.18 vs $15.00 per million) and work measured by LiveBench coding or Terminal-Bench 4 (Vals AI), where it leads.

Model AKimi K3Moonshot AI62.3/1006 independent benchmarks$0.81 per solved taskModel BMistral Large 4Mistral AI56.4/1005 independent benchmarksNo cost per solved task
Shared results
75
Kimi K3 only
42
Mistral Large 4 only
6
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, Mistral Large 4 56.4 from 5 benchmarks.
Widest category
Math, 19.2 points apart on average over 6 shared benchmarks.
Widest single gap
ProofBench: Kimi K3 87.0% against Mistral Large 4 10.0%, 77.0 points apart on a 0 to 100 scale.
Output price
Kimi K3 $15.00 against Mistral Large 4 $4.18 per million output tokens, 3.6x 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 K3BarsMistral Large 4Ties
Coding123
Intelligence20
Agentic work72
Reasoning80
Math51
Knowledge60
Web design80
General201
All shared boards687
CodingLike-for-likeSix of these boards feed the Vibe Coding Index123
Coding benchmarks for Kimi K3 and Mistral Large 4
BenchmarkKimi K3Mistral Large 4Leader
LiveBench coding59.3%60.0%Mistral Large 4
LMArena WebDev16551543Kimi K3
AA Coding Index76.2Not measuredOnly Kimi K3 measured
LiveCodeBench (Vals AI)87.2%Not measuredOnly Kimi K3 measured
SWE-bench Verified (Vals AI)93.4%Not measuredOnly Kimi K3 measured
Terminal-Bench 4 (Vals AI)17.2%27.8%Mistral Large 4
Vibe Code Bench (Vals AI)85.0%78.4%Kimi K3
Code migration (Vals AI)16.1%30.6%Mistral Large 4
ProgramBench (Vals AI)2.0%Not measuredOnly Kimi K3 measured
IOI (Vals AI)48.9%45.3%Kimi K3
Terminal-Bench 2.1 (Vals AI)80.9%Not measuredOnly Kimi K3 measured
SWE-bench Multimodal (Vals AI)44.2%33.1%Kimi K3
Vibe Code Bench 1-100 (Vals AI)18.2%14.3%Kimi K3
CyberBench (Vals AI)75.2%Not measuredOnly Kimi K3 measured
SciCode59.5%54.2%Kimi K3
FrontierCode44.2%39.4%Kimi K3
FrontierSWE25.9%Not measuredOnly Kimi K3 measured
WeirdML82.6%Not measuredOnly Kimi K3 measured
ALE-Bench1524.51213.2Kimi K3
LMArena Text: coding15081478Kimi K3
LMArena Text: software and IT14991467Kimi K3
LMArena WebDev: React16701559Kimi K3
LMArena WebDev: HTML16441487Kimi K3
LMArena WebDev: from an image1579Not measuredOnly Kimi K3 measured
Neither model has a result on the other 15 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Kimi K3 and Mistral Large 4
BenchmarkKimi K3Mistral Large 4Leader
AA Intelligence Index43.638.4Kimi K3
Epoch Capabilities Index157.9150.0Kimi K3
Agentic workLike-for-likePublic boards, shown as published, kept out of the index72
Agentic work benchmarks for Kimi K3 and Mistral Large 4
BenchmarkKimi K3Mistral Large 4Leader
AA Agentic Index50.0Not measuredOnly Kimi K3 measured
Design Arena: agents building web apps1295Not measuredOnly Kimi K3 measured
Design Arena: agents building full-stack apps1315Not measuredOnly Kimi K3 measured
Design Arena: agents building mobile apps1269Not measuredOnly Kimi K3 measured
Design Arena: agents building Android apps1253Not 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 slides1206Not measuredOnly Kimi K3 measured
Design Arena: PowerPoint slides1247Not measuredOnly Kimi K3 measured
Design Arena: spreadsheets1070Not measuredOnly Kimi K3 measured
LiveBench research79.0%28.1%Kimi K3
LiveBench browser16.0%8.0%Kimi K3
LiveBench long agentic42.8%11.8%Kimi K3
Finance Agent (Vals AI)53.1%54.7%Mistral Large 4
Tax Agent Bench (Vals AI)33.4%30.4%Kimi K3
Legal Research Bench (Vals AI)46.1%31.7%Kimi K3
Harvey's Legal Agent Benchmark (Vals AI)12.9%17.5%Mistral Large 4
Excel Modeling Benchmark (Vals AI)66.7%56.2%Kimi K3
BioMysteryBench (Vals AI)72.6%67.0%Kimi K3
Terminal-Bench-Science (Vals AI)1.4%Not measuredOnly Kimi K3 measured
Time Horizon Index (Vals AI)10.5%Not measuredOnly Kimi K3 measured
APEX-Agents47.8%Not measuredOnly Kimi K3 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 17 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index80
Reasoning benchmarks for Kimi K3 and Mistral Large 4
BenchmarkKimi K3Mistral Large 4Leader
GPQA Diamond92.9%Not measuredOnly Kimi K3 measured
LiveBench reasoning90.7%83.9%Kimi K3
MysteryMechanism (Vals AI)Not measured12.2%Only Mistral Large 4 measured
MMMU Pro (Vals AI)88.2%Not measuredOnly Kimi K3 measured
GPQA Diamond (Artificial Analysis run)93.5%Not measuredOnly Kimi K3 measured
Humanity's Last Exam (Artificial Analysis run)46.9%35.0%Kimi K3
GPQA Diamond (Epoch AI run)93.1%88.1%Kimi K3
ARC-AGI94.5%Not measuredOnly Kimi K3 measured
ARC-AGI-260.4%Not measuredOnly Kimi K3 measured
SimpleBench60.7%Not measuredOnly Kimi K3 measured
Chess puzzles37.0%33.0%Kimi K3
Mystery game puzzles26.0%17.0%Kimi K3
LMArena Text: hard prompts14951444Kimi K3
LMArena Text: expert15201444Kimi K3
LMArena Text: hard prompts in English14961442Kimi K3
LMArena Vision: diagramsNot measured1288Only Mistral Large 4 measured
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index51
Math benchmarks for Kimi K3 and Mistral Large 4
BenchmarkKimi K3Mistral Large 4Leader
OTIS Mock AIME97.2%98.3%Mistral Large 4
FrontierMath, tiers 1 to 372.2%58.6%Kimi K3
FrontierMath, tier 439.0%26.8%Kimi K3
ProofBench87.0%10.0%Kimi K3
LMArena Text: math14941469Kimi K3
LMArena Text: mathematical work15051462Kimi K3
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index60
Knowledge benchmarks for Kimi K3 and Mistral Large 4
BenchmarkKimi K3Mistral Large 4Leader
MMLU Pro88.0%Not measuredOnly Kimi K3 measured
LegalBench (Vals AI)86.2%Not measuredOnly Kimi K3 measured
CorpFin (Vals AI)71.6%Not measuredOnly Kimi K3 measured
TaxEval (Vals AI)75.7%Not measuredOnly Kimi K3 measured
MortgageTax (Vals AI)66.3%Not measuredOnly Kimi K3 measured
MedCode (Vals AI)49.4%40.7%Kimi K3
SimpleQA Verified50.6%20.0%Kimi K3
LMArena Text: science15081448Kimi K3
LMArena Text: medicine and healthcare14891433Kimi K3
LMArena Text: legal and government15031425Kimi K3
LMArena Text: business and finance14701439Kimi 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 Mistral Large 4
BenchmarkKimi K3Mistral Large 4Leader
Design Arena: websites13341257Kimi K3
Design Arena: UI components13411272Kimi K3
Design Arena: game dev13581225Kimi K3
Design Arena: data viz13511275Kimi K3
Design Arena: 3D13871252Kimi K3
Design Arena: all code categories13601259Kimi K3
Design Arena: SVG13021232Kimi K3
Design Arena: ASCII artNot measured1202Only Mistral Large 4 measured
LiveBench design77.2%65.6%Kimi K3
GeneralLike-for-likePublic boards, shown as published, kept out of the index201
General benchmarks for Kimi K3 and Mistral Large 4
BenchmarkKimi K3Mistral Large 4Leader
Vals Index53.0%Not measuredOnly Kimi K3 measured
LiveBench data analysis78.7%76.5%Kimi K3
Public Benefits Bench (Vals AI)68.2%Not measuredOnly Kimi K3 measured
SAGE (Vals AI)52.8%Not measuredOnly Kimi K3 measured
MedScribe (Vals AI)88.0%80.4%Kimi K3
Vals Multimodal Index73.4%Not measuredOnly Kimi K3 measured
Long context reasoning (AA-LCR)88.7%81.3%Kimi K3
DTBench91.2%88.2%Kimi K3
LMCA52.7%35.8%Kimi K3
Surface Evolver Bench95.0%28.1%Kimi K3
Furniture assembly34.2%20.8%Kimi K3
LMArena Text14761431Kimi K3
LMArena Text: instruction following14851422Kimi K3
LMArena Text: creative writing14571363Kimi K3
LMArena VisionNot measured1272Only Mistral Large 4 measured
LMArena Text: English14811433Kimi K3
LMArena Text: non-English14661422Kimi K3
LMArena Text: Chinese15291492Kimi K3
LMArena Text: German1490Not measuredOnly Kimi K3 measured
LMArena Text: Japanese14941415Kimi K3
LMArena Text: Korean1460Not measuredOnly Kimi K3 measured
LMArena Text: French14921492Mistral Large 4
LMArena Text: Spanish14721455Kimi K3
LMArena Text: Russian14851417Kimi K3
LMArena Text: Polish1458Not measuredOnly Kimi K3 measured
LMArena Text: multi-turn14891435Kimi K3
LMArena Text: longer queries14941428Kimi K3
LMArena Text: writing and language14711386Kimi K3
LMArena Text: entertainment and media14531378Kimi K3
LMArena Vision: EnglishNot measured1283Only Mistral Large 4 measured
LMArena Vision: reading textNot measured1284Only Mistral Large 4 measured
Neither model has a result on the other 15 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Kimi K3 and Mistral Large 4
BenchmarkKimi K3Mistral Large 4Leader
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
Mistral Large 4$0.0034Fits in one request

Mistral Large 4 costs less

Repository review

50K input + 3K output tokens

Kimi K3$0.195Fits in one request
Mistral Large 4$0.081Fits in one request

Mistral Large 4 costs less

Agent loop

200K input + 10K output tokens

Kimi K3$0.750Fits in one request
Mistral Large 4$0.314Fits in one request

Mistral Large 4 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 Mistral Large 4
SpecificationMoonshotAI Kimi K3Mistral Large 4
MakerMoonshot AIMistral AI
WeightsOpen weightsNo public weights listed
ReleasedJuly 16, 2026October 6, 2026
Context window1.05M1.05M
Input $/Mtok$3.00$1.36
Output $/Mtok$15.00$4.18
Coding index62.356.4
Independent measurements behind it65
Cost per solved task$0.81Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Kimi K3 better than Mistral Large 4 for coding?

Pick Kimi K3 for coding: it scores 62.3 on the Vibe Coding Index against 56.4 for Mistral Large 4. Pick Mistral Large 4 for output tokens 3.6x cheaper ($4.18 vs $15.00 per million) and work measured by LiveBench coding or Terminal-Bench 4 (Vals AI), where it leads.

Which is cheaper, Kimi K3 or Mistral Large 4?

Kimi K3 costs $3.00 per million input tokens and $15.00 per million output tokens; Mistral Large 4 costs $1.36 and $4.18. Cost per solved task is known for Kimi K3 only.

Which has the bigger context window, Kimi K3 or Mistral Large 4?

Neither: both take 1.05M tokens.

How many benchmarks is the Kimi K3 vs Mistral Large 4 comparison based on?

75 benchmarks have a result for both models as of October 22, 2026. Kimi K3's coding index rests on 6 independent benchmarks and Mistral Large 4's on 5. 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-mistral-large-4-0" title="Kimi K3 vs Mistral Large 4, 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-mistral-large-4-0">LLMBenchmark.ai, Kimi K3 vs Mistral Large 4</a></p>