Enter opens the highlighted result. Esc closes.

Kimi K2 0711 vs Mistral Medium 3.1

Kimi K2 0711 leads Mistral Medium 3.1 on the Artificial Analysis Intelligence Index, 12.7 to 9.2, at about the same output price ($2.30 vs $2.00 per million). Updated October 21, 2026; 25 benchmarks have a result for both.

Replace Kimi K2 0711 Replace Mistral Medium 3.1
Kimi K2 0711Moonshot AI
Coding
No data
Overall
12.7
Output $/M
$2.30
18
Mistral Medium 3.1Mistral AI
Coding
No data
Overall
9.2
Output $/M
$2.00
7
vs boards won of 25 shared

Kimi K2 0711 or Mistral Medium 3.1: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick Kimi K2 0711 for work measured by CorpFin (Vals AI) or TaxEval (Vals AI), where it leads.

Model AKimi K2 0711Moonshot AINot benchmarkedNo coding benchmarkNo cost per solved taskModel BMistral Medium 3.1Mistral AINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
25
Kimi K2 0711 only
11
Mistral Medium 3.1 only
49
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 K2 0711 not benchmarked, Mistral Medium 3.1 not benchmarked.
Widest category
Agentic work, 20.5 points apart on average over 1 shared benchmark.
Widest single gap
LiveCodeBench (Vals AI): Kimi K2 0711 70.5% against Mistral Medium 3.1 44.8%, 25.6 points apart on a 0 to 100 scale.
Output price
Kimi K2 0711 $2.30 against Mistral Medium 3.1 $2.00 per million output tokens, 1.1x apart.
Context window
Both take 131K 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 K2 0711BarsMistral Medium 3.1Ties
Coding30
Intelligence10
Agentic work10
Reasoning20
Math50
Knowledge42
Web design05
General20
All shared boards187
CodingLike-for-likeSix of these boards feed the Vibe Coding Index30
Coding benchmarks for Kimi K2 0711 and Mistral Medium 3.1
BenchmarkKimi K2 0711Mistral Medium 3.1Leader
Aider polyglot59.1%Not measuredOnly Kimi K2 0711 measured
SWE-bench Verified71.2%Not measuredOnly Kimi K2 0711 measured
AA Coding IndexNot measured20.5Only Mistral Medium 3.1 measured
LiveCodeBench (Vals AI)70.5%44.8%Kimi K2 0711
LiveCodeBench (Artificial Analysis run)55.6%40.6%Kimi K2 0711
SciCodeNot measured32.4%Only Mistral Medium 3.1 measured
Terminal-Bench Hard (Artificial Analysis run)15.9%10.6%Kimi K2 0711
Terminal-Bench27.8%Not measuredOnly Kimi K2 0711 measured
GSO-Bench4.9%Not measuredOnly Kimi K2 0711 measured
WeirdML39.4%Not measuredOnly Kimi K2 0711 measured
ALE-BenchNot measured210.2Only Mistral Medium 3.1 measured
LMArena Text: codingNot measured1433Only Mistral Medium 3.1 measured
LMArena Text: software and ITNot measured1436Only Mistral Medium 3.1 measured
Neither model has a result on the other 25 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for Kimi K2 0711 and Mistral Medium 3.1
BenchmarkKimi K2 0711Mistral Medium 3.1Leader
AA Intelligence Index12.79.2Kimi K2 0711
Epoch Capabilities Index140.0Not measuredOnly Kimi K2 0711 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for Kimi K2 0711 and Mistral Medium 3.1
BenchmarkKimi K2 0711Mistral Medium 3.1Leader
AA Agentic IndexNot measured1.9Only Mistral Medium 3.1 measured
τ²-Bench Telecom61.1%40.6%Kimi K2 0711
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index20
Reasoning benchmarks for Kimi K2 0711 and Mistral Medium 3.1
BenchmarkKimi K2 0711Mistral Medium 3.1Leader
GPQA Diamond71.5%Not measuredOnly Kimi K2 0711 measured
MMMU Pro (Vals AI)Not measured63.0%Only Mistral Medium 3.1 measured
GPQA Diamond (Artificial Analysis run)76.6%58.8%Kimi K2 0711
Humanity's Last Exam (Artificial Analysis run)7.4%4.7%Kimi K2 0711
SimpleBench26.3%Not measuredOnly Kimi K2 0711 measured
LMArena Text: hard promptsNot measured1426Only Mistral Medium 3.1 measured
LMArena Text: expertNot measured1408Only Mistral Medium 3.1 measured
LMArena Text: hard prompts in EnglishNot measured1435Only Mistral Medium 3.1 measured
LMArena Vision: diagramsNot measured1175Only Mistral Medium 3.1 measured
LMArena Vision: homeworkNot measured1165Only Mistral Medium 3.1 measured
Neither model has a result on the other 11 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index50
Math benchmarks for Kimi K2 0711 and Mistral Medium 3.1
BenchmarkKimi K2 0711Mistral Medium 3.1Leader
AIME62.7%42.3%Kimi K2 0711
MATH 500 (Vals AI)94.2%87.0%Kimi K2 0711
MGSM (Vals AI)91.0%90.9%Kimi K2 0711
AA Math Index57.038.3Kimi K2 0711
AIME 2025 (Artificial Analysis run)57.0%38.3%Kimi K2 0711
LMArena Text: mathNot measured1408Only Mistral Medium 3.1 measured
LMArena Text: mathematical workNot measured1412Only Mistral Medium 3.1 measured
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index42
Knowledge benchmarks for Kimi K2 0711 and Mistral Medium 3.1
BenchmarkKimi K2 0711Mistral Medium 3.1Leader
MMLU Pro79.4%75.3%Kimi K2 0711
LegalBench (Vals AI)81.5%62.0%Kimi K2 0711
CorpFin (Vals AI)50.4%50.7%Mistral Medium 3.1
TaxEval (Vals AI)70.2%70.3%Mistral Medium 3.1
MortgageTax (Vals AI)Not measured36.5%Only Mistral Medium 3.1 measured
MedQA (Vals AI)84.0%78.2%Kimi K2 0711
MMLU Pro (Artificial Analysis run)82.4%68.3%Kimi K2 0711
LMArena Text: scienceNot measured1444Only Mistral Medium 3.1 measured
LMArena Text: medicine and healthcareNot measured1449Only Mistral Medium 3.1 measured
LMArena Text: legal and governmentNot measured1439Only Mistral Medium 3.1 measured
LMArena Text: business and financeNot measured1418Only Mistral Medium 3.1 measured
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index05
Web design benchmarks for Kimi K2 0711 and Mistral Medium 3.1
BenchmarkKimi K2 0711Mistral Medium 3.1Leader
Design Arena: websites10501133Mistral Medium 3.1
Design Arena: UI components10301100Mistral Medium 3.1
Design Arena: game dev9741074Mistral Medium 3.1
Design Arena: data viz10181144Mistral Medium 3.1
Design Arena: 3DNot measured1081Only Mistral Medium 3.1 measured
Design Arena: all code categories10331120Mistral Medium 3.1
Design Arena: SVGNot measured993Only Mistral Medium 3.1 measured
Design Arena: ASCII artNot measured997Only Mistral Medium 3.1 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index20
General benchmarks for Kimi K2 0711 and Mistral Medium 3.1
BenchmarkKimi K2 0711Mistral Medium 3.1Leader
IFBench41.5%39.8%Kimi K2 0711
Long context reasoning (AA-LCR)53.0%42.7%Kimi K2 0711
DTBenchNot measured67.5%Only Mistral Medium 3.1 measured
LMCANot measured19.1%Only Mistral Medium 3.1 measured
Fiction.LiveBench61.1%Not measuredOnly Kimi K2 0711 measured
Creative writing (Lech Mazur)85.6%Not measuredOnly Kimi K2 0711 measured
CL-bench11.9%Not measuredOnly Kimi K2 0711 measured
LMArena TextNot measured1424Only Mistral Medium 3.1 measured
LMArena Text: instruction followingNot measured1398Only Mistral Medium 3.1 measured
LMArena Text: creative writingNot measured1391Only Mistral Medium 3.1 measured
LMArena VisionNot measured1172Only Mistral Medium 3.1 measured
LMArena Text: EnglishNot measured1438Only Mistral Medium 3.1 measured
LMArena Text: non-EnglishNot measured1408Only Mistral Medium 3.1 measured
LMArena Text: ChineseNot measured1447Only Mistral Medium 3.1 measured
LMArena Text: GermanNot measured1432Only Mistral Medium 3.1 measured
LMArena Text: JapaneseNot measured1379Only Mistral Medium 3.1 measured
LMArena Text: KoreanNot measured1380Only Mistral Medium 3.1 measured
LMArena Text: FrenchNot measured1460Only Mistral Medium 3.1 measured
LMArena Text: SpanishNot measured1433Only Mistral Medium 3.1 measured
LMArena Text: RussianNot measured1411Only Mistral Medium 3.1 measured
LMArena Text: PolishNot measured1430Only Mistral Medium 3.1 measured
LMArena Text: multi-turnNot measured1418Only Mistral Medium 3.1 measured
LMArena Text: longer queriesNot measured1406Only Mistral Medium 3.1 measured
LMArena Text: writing and languageNot measured1395Only Mistral Medium 3.1 measured
LMArena Text: entertainment and mediaNot measured1390Only Mistral Medium 3.1 measured
LMArena Vision: EnglishNot measured1179Only Mistral Medium 3.1 measured
LMArena Vision: ChineseNot measured1190Only Mistral Medium 3.1 measured
LMArena Vision: reading textNot measured1175Only Mistral Medium 3.1 measured
LMArena Vision: humorNot measured1168Only Mistral Medium 3.1 measured
LMArena Vision: captioningNot measured1145Only Mistral Medium 3.1 measured
LMArena Vision: recognizing thingsNot measured1147Only Mistral Medium 3.1 measured
LMArena Vision: creative writingNot measured1200Only Mistral Medium 3.1 measured
Neither model has a result on the other 14 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Kimi K2 0711 and Mistral Medium 3.1
BenchmarkKimi K2 0711Mistral Medium 3.1Leader
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 0711$0.0017Fits in one request
Mistral Medium 3.1$0.0014Fits in one request

Mistral Medium 3.1 costs less

Repository review

50K input + 3K output tokens

Kimi K2 0711$0.035Fits in one request
Mistral Medium 3.1$0.026Fits in one request

Mistral Medium 3.1 costs less

Agent loop

200K input + 10K output tokens

Kimi K2 0711$0.137Exceeds the context window
Mistral Medium 3.1$0.100Exceeds the context window

Mistral Medium 3.1 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 0711 and Mistral Medium 3.1
SpecificationMoonshotAI Kimi K2 0711Mistral Medium 3.1
MakerMoonshot AIMistral AI
WeightsOpen weightsNo public weights listed
ReleasedJuly 11, 2025August 13, 2025
Context window131K131K
Input $/Mtok$0.57$0.40
Output $/Mtok$2.30$2.00
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Kimi K2 0711 better than Mistral Medium 3.1 for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Kimi K2 0711 for work measured by CorpFin (Vals AI) or TaxEval (Vals AI), where it leads.

Which is cheaper, Kimi K2 0711 or Mistral Medium 3.1?

Kimi K2 0711 costs $0.57 per million input tokens and $2.30 per million output tokens; Mistral Medium 3.1 costs $0.40 and $2.00. Cost per solved task is known for neither of them.

Which has the bigger context window, Kimi K2 0711 or Mistral Medium 3.1?

Neither: both take 131K tokens.

How many benchmarks is the Kimi K2 0711 vs Mistral Medium 3.1 comparison based on?

25 benchmarks have a result for both models as of October 21, 2026. Kimi K2 0711's coding index rests on 0 independent benchmarks and Mistral Medium 3.1's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next