Enter opens the highlighted result. Esc closes.

Kimi K2.5 vs Mistral Medium 3

Updated October 21, 2026. 52 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Kimi K2.5 Replace Mistral Medium 3
Kimi K2.5Moonshot AI
Coding
38.6
Overall
23.5
Output $/M
$2.85
52
Mistral Medium 3Mistral AI
Coding
No data
Overall
9.0
Output $/M
$2.00
0
vs boards won of 52 shared

Decision reading

Only Kimi K2.5 has a coding score, 38.6 on the Vibe Coding Index; Mistral Medium 3 has none, so the two cannot be ranked on coding.

Mistral Medium 3 has the edge where output tokens cost 1.4x less.

Model AKimi K2.5Moonshot AI38.6/1003 independent benchmarks$0.24 per solved taskModel BMistral Medium 3Mistral AINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
52
Kimi K2.5 only
46
Mistral Medium 3 only
5
Like-for-like categories
8 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 K2.5 38.6 from 3 benchmarks, Mistral Medium 3 not benchmarked.
Widest category
Agentic work, 71.6 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: Kimi K2.5 95.9% against Mistral Medium 3 24.3%, 71.6 points apart on a 0 to 100 scale.
Output price
Kimi K2.5 $2.85 against Mistral Medium 3 $2.00 per million output tokens, 1.4x apart.
Context window
Kimi K2.5 takes 262K tokens, Mistral Medium 3 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 3Ties
Coding30
Intelligence20
Agentic work10
Reasoning70
Math20
Knowledge40
Web design60
General270
All shared boards520
CodingLike-for-likeSix of these boards feed the Vibe Coding Index30
Coding benchmarks for Kimi K2.5 and Mistral Medium 3
BenchmarkKimi K2.5Mistral Medium 3Leader
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 Index46.8Not measuredOnly Kimi K2.5 measured
LiveCodeBench (Vals AI)83.9%Not measuredOnly Kimi K2.5 measured
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 measured40.0%Only Mistral Medium 3 measured
Terminal-Bench Hard (Artificial Analysis run)34.8%3.8%Kimi K2.5
Terminal-Bench43.2%Not measuredOnly Kimi K2.5 measured
WeirdML45.6%Not measuredOnly Kimi K2.5 measured
ALE-Bench821.6Not measuredOnly Kimi K2.5 measured
LMArena Text: coding14831385Kimi K2.5
LMArena Text: software and IT14711385Kimi 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 index20
Intelligence benchmarks for Kimi K2.5 and Mistral Medium 3
BenchmarkKimi K2.5Mistral Medium 3Leader
AA Intelligence Index23.59.0Kimi K2.5
Epoch Capabilities Index148.1134.0Kimi K2.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for Kimi K2.5 and Mistral Medium 3
BenchmarkKimi K2.5Mistral Medium 3Leader
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 apps1125Not 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%24.3%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 28 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index70
Reasoning benchmarks for Kimi K2.5 and Mistral Medium 3
BenchmarkKimi K2.5Mistral Medium 3Leader
GPQA Diamond84.1%Not measuredOnly Kimi K2.5 measured
MMMU Pro (Vals AI)84.3%Not measuredOnly Kimi K2.5 measured
GPQA Diamond (Artificial Analysis run)87.9%57.8%Kimi K2.5
Humanity's Last Exam (Artificial Analysis run)30.7%4.1%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 prompts14531364Kimi K2.5
LMArena Text: expert14661342Kimi K2.5
LMArena Text: hard prompts in English14601374Kimi K2.5
LMArena Vision: diagrams12821155Kimi K2.5
LMArena Vision: homework12971165Kimi K2.5
Neither model has a result on the other 9 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index20
Math benchmarks for Kimi K2.5 and Mistral Medium 3
BenchmarkKimi K2.5Mistral Medium 3Leader
AIME95.6%Not measuredOnly Kimi K2.5 measured
AA Math IndexNot measured30.3Only Mistral Medium 3 measured
AIME 2025 (Artificial Analysis run)Not measured30.3%Only Mistral Medium 3 measured
LMArena Text: math14701353Kimi K2.5
LMArena Text: mathematical work14731354Kimi K2.5
Neither model has a result on the other 8 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
Knowledge benchmarks for Kimi K2.5 and Mistral Medium 3
BenchmarkKimi K2.5Mistral Medium 3Leader
MMLU Pro85.9%Not measuredOnly Kimi K2.5 measured
CaseLaw (Vals AI)58.7%Not measuredOnly Kimi K2.5 measured
CorpFin (Vals AI)68.3%Not measuredOnly Kimi K2.5 measured
TaxEval (Vals AI)74.2%Not measuredOnly Kimi K2.5 measured
MortgageTax (Vals AI)66.5%Not measuredOnly Kimi K2.5 measured
MedQA (Vals AI)94.4%Not measuredOnly Kimi K2.5 measured
MedCode (Vals AI)39.3%Not measuredOnly Kimi K2.5 measured
MMLU Pro (Artificial Analysis run)Not measured76.0%Only Mistral Medium 3 measured
SimpleQA Verified34.3%Not measuredOnly Kimi K2.5 measured
LMArena Text: science14591381Kimi K2.5
LMArena Text: medicine and healthcare14481381Kimi K2.5
LMArena Text: legal and government14411384Kimi K2.5
LMArena Text: business and finance14271352Kimi 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 index60
Web design benchmarks for Kimi K2.5 and Mistral Medium 3
BenchmarkKimi K2.5Mistral Medium 3Leader
Design Arena: websites12491079Kimi K2.5
Design Arena: UI components12361024Kimi K2.5
Design Arena: game dev12071018Kimi K2.5
Design Arena: data viz12181034Kimi K2.5
Design Arena: 3D12051083Kimi K2.5
Design Arena: all code categories12361069Kimi K2.5
Design Arena: SVG1149Not measuredOnly Kimi K2.5 measured
Design Arena: ASCII art1165Not measuredOnly Kimi K2.5 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index270
General benchmarks for Kimi K2.5 and Mistral Medium 3
BenchmarkKimi K2.5Mistral Medium 3Leader
SAGE (Vals AI)49.9%Not measuredOnly Kimi K2.5 measured
MedScribe (Vals AI)76.4%Not measuredOnly Kimi K2.5 measured
IFBench70.2%39.3%Kimi K2.5
Long context reasoning (AA-LCR)78.0%31.3%Kimi K2.5
DTBenchNot measured62.3%Only Mistral Medium 3 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 Text14451370Kimi K2.5
LMArena Text: instruction following14311338Kimi K2.5
LMArena Text: creative writing14221343Kimi K2.5
LMArena Vision12691157Kimi K2.5
LMArena Text: English14531385Kimi K2.5
LMArena Text: non-English14331353Kimi K2.5
LMArena Text: Chinese14941374Kimi K2.5
LMArena Text: German14411377Kimi K2.5
LMArena Text: Japanese14231316Kimi K2.5
LMArena Text: Korean14121304Kimi K2.5
LMArena Text: French14541368Kimi K2.5
LMArena Text: Spanish14501364Kimi K2.5
LMArena Text: Russian14351359Kimi K2.5
LMArena Text: Polish14451371Kimi K2.5
LMArena Text: multi-turn14441384Kimi K2.5
LMArena Text: longer queries14451360Kimi K2.5
LMArena Text: writing and language14251352Kimi K2.5
LMArena Text: entertainment and media14171335Kimi K2.5
LMArena Vision: English12741172Kimi K2.5
LMArena Vision: Chinese13281161Kimi K2.5
LMArena Vision: reading text12761154Kimi K2.5
LMArena Vision: humor12841145Kimi K2.5
LMArena Vision: captioning12571094Kimi K2.5
LMArena Vision: recognizing things12851141Kimi K2.5
LMArena Vision: creative writing12691146Kimi K2.5
Neither model has a result on the other 13 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
BenchmarkKimi K2.5Mistral Medium 3Leader
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$0.0014Fits in one request

Mistral Medium 3 costs less

Repository review

50K input + 3K output tokens

Kimi K2.5$0.035Fits in one request
Mistral Medium 3$0.026Fits in one request

Mistral Medium 3 costs less

Agent loop

200K input + 10K output tokens

Kimi K2.5$0.135Fits in one request
Mistral Medium 3$0.100Exceeds the context window

Mistral Medium 3 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
SpecificationMoonshotAI Kimi K2.5Mistral Medium 3
MakerMoonshot AIMistral AI
WeightsOpen weightsNo public weights listed
ReleasedJanuary 27, 2026May 7, 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 for coding?

Only Kimi K2.5 has a coding score, 38.6 on the Vibe Coding Index; Mistral Medium 3 has none, so the two cannot be ranked on coding. Mistral Medium 3 has the edge where output tokens cost 1.4x less.

Which is cheaper, Kimi K2.5 or Mistral Medium 3?

Kimi K2.5 costs $0.532 per million input tokens and $2.85 per million output tokens; Mistral Medium 3 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?

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

How many benchmarks is the Kimi K2.5 vs Mistral Medium 3 comparison based on?

52 benchmarks have a result for both models as of October 21, 2026. Kimi K2.5's coding index rests on 3 independent benchmarks and Mistral Medium 3's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next