Enter opens the highlighted result. Esc closes.

Kimi K2.5 vs Mistral Medium 3.1

Kimi K2.5 leads Mistral Medium 3.1 on the Artificial Analysis Intelligence Index, 23.5 to 9.2, and Mistral Medium 3.1 costs 1.4x less per output token ($2.00 vs $2.85 per million). Updated October 22, 2026; 63 benchmarks have a result for both.

Replace Kimi K2.5 Replace Mistral Medium 3.1
Kimi K2.5Moonshot AI
Coding
38.6
Overall
44.8
Output $/M
$2.85
61
Mistral Medium 3.1Mistral AI
Coding
No data
Overall
No data
Output $/M
$2.00
2
vs boards won of 63 shared

Kimi K2.5 or Mistral Medium 3.1: which to pick

Only Kimi K2.5 has a coding score, 38.6 on the Vibe Coding Index; Mistral Medium 3.1 has none, so the two cannot be ranked on coding.

Pick Mistral Medium 3.1 for output tokens 1.4x cheaper ($2.00 vs $2.85 per million) and work measured by LMArena Text: medicine and healthcare or LMArena Text: French, where it leads.

Model AKimi K2.5Moonshot AI38.6/1003 independent benchmarks$0.24 per solved taskModel BMistral Medium 3.1Mistral AINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
63
Kimi K2.5 only
36
Mistral Medium 3.1 only
11
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 K2.5 38.6 from 3 benchmarks, Mistral Medium 3.1 not benchmarked.
Widest category
Agentic work, 55.3 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: Kimi K2.5 95.9% against Mistral Medium 3.1 40.6%, 55.3 points apart on a 0 to 100 scale.
Output price
Kimi K2.5 $2.85 against Mistral Medium 3.1 $2.00 per million output tokens, 1.4x apart.
Context window
Kimi K2.5 takes 262K tokens, Mistral Medium 3.1 131K.

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 K2.5BarsMistral Medium 3.1Ties
Coding60
Intelligence10
Agentic work10
Reasoning80
Math30
Knowledge81
Web design80
General261
All shared boards612
CodingLike-for-likeSix of these boards feed the Vibe Coding Index60
Coding benchmarks for Kimi K2.5 and Mistral Medium 3.1
BenchmarkKimi K2.5Mistral Medium 3.1Leader
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 Index46.820.5Kimi K2.5
LiveCodeBench (Vals AI)83.9%44.8%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 measured40.6%Only Mistral Medium 3.1 measured
SciCodeNot measured32.4%Only Mistral Medium 3.1 measured
Terminal-Bench Hard (Artificial Analysis run)34.8%10.6%Kimi K2.5
Terminal-Bench43.2%Not measuredOnly Kimi K2.5 measured
WeirdML45.6%Not measuredOnly Kimi K2.5 measured
ALE-Bench821.6210.2Kimi K2.5
LMArena Text: coding14831433Kimi K2.5
LMArena Text: software and IT14711436Kimi 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
Neither model has a result on the other 19 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for Kimi K2.5 and Mistral Medium 3.1
BenchmarkKimi K2.5Mistral Medium 3.1Leader
AA Intelligence Index23.59.2Kimi K2.5
Epoch Capabilities Index148.1Not measuredOnly Kimi K2.5 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for Kimi K2.5 and Mistral Medium 3.1
BenchmarkKimi K2.5Mistral Medium 3.1Leader
AA Agentic IndexNot measured1.9Only Mistral Medium 3.1 measured
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%40.6%Kimi K2.5
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 index80
Reasoning benchmarks for Kimi K2.5 and Mistral Medium 3.1
BenchmarkKimi K2.5Mistral Medium 3.1Leader
GPQA Diamond84.1%Not measuredOnly Kimi K2.5 measured
MMMU Pro (Vals AI)84.3%63.0%Kimi K2.5
GPQA Diamond (Artificial Analysis run)87.9%58.8%Kimi K2.5
Humanity's Last Exam (Artificial Analysis run)30.7%4.7%Kimi K2.5
ARC-AGI65.3%Not measuredOnly Kimi K2.5 measured
ARC-AGI-211.8%Not measuredOnly Kimi K2.5 measured
SimpleBench46.8%Not measuredOnly Kimi K2.5 measured
LMArena Text: hard prompts14531426Kimi K2.5
LMArena Text: expert14661408Kimi K2.5
LMArena Text: hard prompts in English14601435Kimi K2.5
LMArena Vision: diagrams12821175Kimi K2.5
LMArena Vision: homework12971165Kimi K2.5
Kagi LLM Benchmark78.5%Not measuredOnly Kimi K2.5 measured
Neither model has a result on the other 9 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index30
Math benchmarks for Kimi K2.5 and Mistral Medium 3.1
BenchmarkKimi K2.5Mistral Medium 3.1Leader
AIME95.6%42.3%Kimi K2.5
MATH 500 (Vals AI)Not measured87.0%Only Mistral Medium 3.1 measured
MGSM (Vals AI)Not measured90.9%Only Mistral Medium 3.1 measured
AA Math IndexNot measured38.3Only Mistral Medium 3.1 measured
AIME 2025 (Artificial Analysis run)Not measured38.3%Only Mistral Medium 3.1 measured
LMArena Text: math14701408Kimi K2.5
LMArena Text: mathematical work14731412Kimi K2.5
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index81
Knowledge benchmarks for Kimi K2.5 and Mistral Medium 3.1
BenchmarkKimi K2.5Mistral Medium 3.1Leader
MMLU Pro85.9%75.3%Kimi K2.5
LegalBench (Vals AI)Not measured62.0%Only Mistral Medium 3.1 measured
CaseLaw (Vals AI)58.7%Not measuredOnly Kimi K2.5 measured
CorpFin (Vals AI)68.3%50.7%Kimi K2.5
TaxEval (Vals AI)74.2%70.3%Kimi K2.5
MortgageTax (Vals AI)66.5%36.5%Kimi K2.5
MedQA (Vals AI)94.4%78.2%Kimi K2.5
MedCode (Vals AI)39.3%Not measuredOnly Kimi K2.5 measured
MMLU Pro (Artificial Analysis run)Not measured68.3%Only Mistral Medium 3.1 measured
SimpleQA Verified34.3%Not measuredOnly Kimi K2.5 measured
LMArena Text: science14591444Kimi K2.5
LMArena Text: medicine and healthcare14481449Mistral Medium 3.1
LMArena Text: legal and government14411439Kimi K2.5
LMArena Text: business and finance14271418Kimi K2.5
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index80
Web design benchmarks for Kimi K2.5 and Mistral Medium 3.1
BenchmarkKimi K2.5Mistral Medium 3.1Leader
Design Arena: websites12481132Kimi K2.5
Design Arena: UI components12341097Kimi K2.5
Design Arena: game dev12061073Kimi K2.5
Design Arena: data viz12191144Kimi K2.5
Design Arena: 3D12041081Kimi K2.5
Design Arena: all code categories12361120Kimi K2.5
Design Arena: SVG1149992Kimi K2.5
Design Arena: ASCII art1166997Kimi K2.5
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index261
General benchmarks for Kimi K2.5 and Mistral Medium 3.1
BenchmarkKimi K2.5Mistral Medium 3.1Leader
SAGE (Vals AI)49.9%Not measuredOnly Kimi K2.5 measured
MedScribe (Vals AI)76.4%Not measuredOnly Kimi K2.5 measured
IFBench70.2%39.8%Kimi K2.5
Long context reasoning (AA-LCR)78.0%42.7%Kimi K2.5
DTBenchNot measured67.5%Only Mistral Medium 3.1 measured
LMCANot measured19.1%Only Mistral Medium 3.1 measured
Fiction.LiveBench86.1%Not measuredOnly Kimi K2.5 measured
CL-bench19.3%Not measuredOnly Kimi K2.5 measured
CL-bench Life13.2%Not measuredOnly Kimi K2.5 measured
LMArena Text14451424Kimi K2.5
LMArena Text: instruction following14311398Kimi K2.5
LMArena Text: creative writing14221391Kimi K2.5
LMArena Vision12691172Kimi K2.5
LMArena Text: English14531438Kimi K2.5
LMArena Text: non-English14331408Kimi K2.5
LMArena Text: Chinese14941447Kimi K2.5
LMArena Text: German14411432Kimi K2.5
LMArena Text: Japanese14231379Kimi K2.5
LMArena Text: Korean14121380Kimi K2.5
LMArena Text: French14541460Mistral Medium 3.1
LMArena Text: Spanish14501433Kimi K2.5
LMArena Text: Russian14351411Kimi K2.5
LMArena Text: Polish14451430Kimi K2.5
LMArena Text: multi-turn14441418Kimi K2.5
LMArena Text: longer queries14451406Kimi K2.5
LMArena Text: writing and language14251395Kimi K2.5
LMArena Text: entertainment and media14171390Kimi K2.5
LMArena Vision: English12741179Kimi K2.5
LMArena Vision: Chinese13281190Kimi K2.5
LMArena Vision: reading text12761175Kimi K2.5
LMArena Vision: humor12841168Kimi K2.5
LMArena Vision: captioning12571145Kimi K2.5
LMArena Vision: recognizing things12851147Kimi K2.5
LMArena Vision: creative writing12691200Kimi K2.5
Neither model has a result on the other 12 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 Mistral Medium 3.1
BenchmarkKimi K2.5Mistral 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 K2.5$0.0020Fits 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 K2.5$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 K2.5$0.135Fits in one request
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 K2.5 and Mistral Medium 3.1
SpecificationMoonshotAI Kimi K2.5Mistral Medium 3.1
MakerMoonshot AIMistral AI
WeightsOpen weightsNo public weights listed
ReleasedJanuary 27, 2026August 13, 2025
Context window262K131K
Input $/Mtok$0.532$0.40
Output $/Mtok$2.85$2.00
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 Mistral Medium 3.1 for coding?

Only Kimi K2.5 has a coding score, 38.6 on the Vibe Coding Index; Mistral Medium 3.1 has none, so the two cannot be ranked on coding. Pick Mistral Medium 3.1 for output tokens 1.4x cheaper ($2.00 vs $2.85 per million) and work measured by LMArena Text: medicine and healthcare or LMArena Text: French, where it leads.

Which is cheaper, Kimi K2.5 or Mistral Medium 3.1?

Kimi K2.5 costs $0.532 per million input tokens and $2.85 per million output tokens; Mistral Medium 3.1 costs $0.40 and $2.00. Cost per solved task is known for Kimi K2.5 only.

Which has the bigger context window, Kimi K2.5 or Mistral Medium 3.1?

Kimi K2.5, with 262K tokens against 131K.

How many benchmarks is the Kimi K2.5 vs Mistral Medium 3.1 comparison based on?

63 benchmarks have a result for both models as of October 22, 2026. Kimi K2.5's coding index rests on 3 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