Enter opens the highlighted result. Esc closes.

Mistral Medium 3.1 vs Mistral Medium 3.5

Updated October 21, 2026. 60 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Mistral Medium 3.1 Replace Mistral Medium 3.5
Mistral Medium 3.1Mistral AI
Coding
No data
Overall
9.2
Output $/M
$2.00
21
Mistral Medium 3.5Mistral AI
Coding
25.5
Overall
14.2
Output $/M
$7.50
39
vs boards won of 60 shared

Decision reading

Only Mistral Medium 3.5 has a coding score, 25.5 on the Vibe Coding Index; Mistral Medium 3.1 has none, so the two cannot be ranked on coding.

Mistral Medium 3.1 has the edge where output tokens cost 3.8x less, and where what matters is TaxEval (Vals AI) or MortgageTax (Vals AI), where it leads.

Model AMistral Medium 3.1Mistral AINot benchmarkedNo coding benchmarkNo cost per solved taskModel BMistral Medium 3.5Mistral AI25.5/1003 independent benchmarks$6.02 per solved task
Shared results
60
Mistral Medium 3.1 only
14
Mistral Medium 3.5 only
20
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
Mistral Medium 3.1 not benchmarked, Mistral Medium 3.5 25.5 from 3 benchmarks.
Widest category
Agentic work, 29.3 points apart on average over 2 shared benchmarks.
Widest single gap
τ²-Bench Telecom: Mistral Medium 3.1 40.6% against Mistral Medium 3.5 94.2%, 53.5 points apart on a 0 to 100 scale.
Output price
Mistral Medium 3.1 $2.00 against Mistral Medium 3.5 $7.50 per million output tokens, 3.8x apart.
Context window
Mistral Medium 3.1 takes 131K tokens, Mistral Medium 3.5 262K.

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
CategoryMistral Medium 3.1BarsMistral Medium 3.5Ties
Coding06
Intelligence01
Agentic work02
Reasoning07
Math02
Knowledge53
Web design44
General1214
All shared boards2139
CodingLike-for-likeSix of these boards feed the Vibe Coding Index06
Coding benchmarks for Mistral Medium 3.1 and Mistral Medium 3.5
BenchmarkMistral Medium 3.1Mistral Medium 3.5Leader
LMArena WebDevNot measured1264Only Mistral Medium 3.5 measured
AA Coding Index20.546.9Mistral Medium 3.5
LiveCodeBench (Vals AI)44.8%Not measuredOnly Mistral Medium 3.1 measured
SWE-bench Verified (Vals AI)Not measured66.4%Only Mistral Medium 3.5 measured
Vibe Code Bench (Vals AI)Not measured2.9%Only Mistral Medium 3.5 measured
Code migration (Vals AI)Not measured5.1%Only Mistral Medium 3.5 measured
Terminal-Bench 2.1 (Vals AI)Not measured39.0%Only Mistral Medium 3.5 measured
LiveCodeBench (Artificial Analysis run)40.6%Not measuredOnly Mistral Medium 3.1 measured
SciCode32.4%40.2%Mistral Medium 3.5
Terminal-Bench Hard (Artificial Analysis run)10.6%33.3%Mistral Medium 3.5
ALE-Bench210.2764.0Mistral Medium 3.5
LMArena Text: coding14331460Mistral Medium 3.5
LMArena Text: software and IT14361458Mistral Medium 3.5
LMArena WebDev: ReactNot measured1254Only Mistral Medium 3.5 measured
LMArena WebDev: HTMLNot measured1308Only Mistral Medium 3.5 measured
Neither model has a result on the other 23 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Mistral Medium 3.1 and Mistral Medium 3.5
BenchmarkMistral Medium 3.1Mistral Medium 3.5Leader
AA Intelligence Index9.214.2Mistral Medium 3.5
Epoch Capabilities IndexNot measured141.4Only Mistral Medium 3.5 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index02
Agentic work benchmarks for Mistral Medium 3.1 and Mistral Medium 3.5
BenchmarkMistral Medium 3.1Mistral Medium 3.5Leader
AA Agentic Index1.97.0Mistral Medium 3.5
Finance Agent (Vals AI)Not measured32.1%Only Mistral Medium 3.5 measured
Tax Agent Bench (Vals AI)Not measured4.5%Only Mistral Medium 3.5 measured
Legal Research Bench (Vals AI)Not measured9.1%Only Mistral Medium 3.5 measured
Excel Modeling Benchmark (Vals AI)Not measured11.2%Only Mistral Medium 3.5 measured
τ²-Bench Telecom40.6%94.2%Mistral Medium 3.5
Neither model has a result on the other 33 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index07
Reasoning benchmarks for Mistral Medium 3.1 and Mistral Medium 3.5
BenchmarkMistral Medium 3.1Mistral Medium 3.5Leader
GPQA DiamondNot measured34.9%Only Mistral Medium 3.5 measured
MMMU Pro (Vals AI)63.0%Not measuredOnly Mistral Medium 3.1 measured
GPQA Diamond (Artificial Analysis run)58.8%74.8%Mistral Medium 3.5
Humanity's Last Exam (Artificial Analysis run)4.7%13.8%Mistral Medium 3.5
LMArena Text: hard prompts14261436Mistral Medium 3.5
LMArena Text: expert14081432Mistral Medium 3.5
LMArena Text: hard prompts in English14351445Mistral Medium 3.5
LMArena Vision: diagrams11751254Mistral Medium 3.5
LMArena Vision: homework11651230Mistral Medium 3.5
Neither model has a result on the other 12 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for Mistral Medium 3.1 and Mistral Medium 3.5
BenchmarkMistral Medium 3.1Mistral Medium 3.5Leader
AIME42.3%Not measuredOnly Mistral Medium 3.1 measured
MATH 500 (Vals AI)87.0%Not measuredOnly Mistral Medium 3.1 measured
MGSM (Vals AI)90.9%Not measuredOnly Mistral Medium 3.1 measured
AA Math Index38.3Not measuredOnly Mistral Medium 3.1 measured
AIME 2025 (Artificial Analysis run)38.3%Not measuredOnly Mistral Medium 3.1 measured
ProofBenchNot measured9.0%Only Mistral Medium 3.5 measured
LMArena Text: math14081431Mistral Medium 3.5
LMArena Text: mathematical work14121440Mistral Medium 3.5
Neither model has a result on the other 5 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index53
Knowledge benchmarks for Mistral Medium 3.1 and Mistral Medium 3.5
BenchmarkMistral Medium 3.1Mistral Medium 3.5Leader
MMLU Pro75.3%75.3%Mistral Medium 3.5
LegalBench (Vals AI)62.0%Not measuredOnly Mistral Medium 3.1 measured
CaseLaw (Vals AI)Not measured44.2%Only Mistral Medium 3.5 measured
CorpFin (Vals AI)50.7%58.8%Mistral Medium 3.5
TaxEval (Vals AI)70.3%68.0%Mistral Medium 3.1
MortgageTax (Vals AI)36.5%28.9%Mistral Medium 3.1
MedQA (Vals AI)78.2%Not measuredOnly Mistral Medium 3.1 measured
MedCode (Vals AI)Not measured33.8%Only Mistral Medium 3.5 measured
MMLU Pro (Artificial Analysis run)68.3%Not measuredOnly Mistral Medium 3.1 measured
LMArena Text: science14441428Mistral Medium 3.1
LMArena Text: medicine and healthcare14491409Mistral Medium 3.1
LMArena Text: legal and government14391437Mistral Medium 3.1
LMArena Text: business and finance14181426Mistral Medium 3.5
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index44
Web design benchmarks for Mistral Medium 3.1 and Mistral Medium 3.5
BenchmarkMistral Medium 3.1Mistral Medium 3.5Leader
Design Arena: websites11331142Mistral Medium 3.5
Design Arena: UI components10991079Mistral Medium 3.1
Design Arena: game dev10741079Mistral Medium 3.5
Design Arena: data viz11441120Mistral Medium 3.1
Design Arena: 3D10811061Mistral Medium 3.1
Design Arena: all code categories11201121Mistral Medium 3.5
Design Arena: SVG993950Mistral Medium 3.1
Design Arena: ASCII art9971062Mistral Medium 3.5
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index1214
General benchmarks for Mistral Medium 3.1 and Mistral Medium 3.5
BenchmarkMistral Medium 3.1Mistral Medium 3.5Leader
SAGE (Vals AI)Not measured37.6%Only Mistral Medium 3.5 measured
MedScribe (Vals AI)Not measured67.7%Only Mistral Medium 3.5 measured
Vals Multimodal IndexNot measured34.8%Only Mistral Medium 3.5 measured
IFBench39.8%68.8%Mistral Medium 3.5
Long context reasoning (AA-LCR)42.7%69.3%Mistral Medium 3.5
DTBench67.5%75.5%Mistral Medium 3.5
LMCA19.1%26.1%Mistral Medium 3.5
Surface Evolver BenchNot measured26.9%Only Mistral Medium 3.5 measured
LMArena Text14241421Mistral Medium 3.1
LMArena Text: instruction following13981415Mistral Medium 3.5
LMArena Text: creative writing13911374Mistral Medium 3.1
LMArena Vision11721222Mistral Medium 3.5
LMArena Text: English14381433Mistral Medium 3.1
LMArena Text: non-English14081404Mistral Medium 3.1
LMArena Text: Chinese14471444Mistral Medium 3.1
LMArena Text: German14321453Mistral Medium 3.5
LMArena Text: Japanese1379Not measuredOnly Mistral Medium 3.1 measured
LMArena Text: Korean13801384Mistral Medium 3.5
LMArena Text: French14601448Mistral Medium 3.1
LMArena Text: Spanish14331411Mistral Medium 3.1
LMArena Text: Russian14111395Mistral Medium 3.1
LMArena Text: Polish14301430Mistral Medium 3.1
LMArena Text: multi-turn14181423Mistral Medium 3.5
LMArena Text: longer queries14061415Mistral Medium 3.5
LMArena Text: writing and language13951384Mistral Medium 3.1
LMArena Text: entertainment and media13901382Mistral Medium 3.1
LMArena Vision: English11791240Mistral Medium 3.5
LMArena Vision: Chinese11901244Mistral Medium 3.5
LMArena Vision: reading text11751233Mistral Medium 3.5
LMArena Vision: humor11681216Mistral Medium 3.5
LMArena Vision: captioning1145Not measuredOnly Mistral Medium 3.1 measured
LMArena Vision: recognizing things1147Not measuredOnly Mistral Medium 3.1 measured
LMArena Vision: creative writing12001198Mistral Medium 3.1
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 Mistral Medium 3.1 and Mistral Medium 3.5
BenchmarkMistral Medium 3.1Mistral Medium 3.5Leader
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

Mistral Medium 3.1$0.0014Fits in one request
Mistral Medium 3.5$0.0053Fits in one request

Mistral Medium 3.1 costs less

Repository review

50K input + 3K output tokens

Mistral Medium 3.1$0.026Fits in one request
Mistral Medium 3.5$0.098Fits in one request

Mistral Medium 3.1 costs less

Agent loop

200K input + 10K output tokens

Mistral Medium 3.1$0.100Exceeds the context window
Mistral Medium 3.5$0.375Fits in one request

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 Mistral Medium 3.1 and Mistral Medium 3.5
SpecificationMistral Medium 3.1Mistral Medium 3.5
MakerMistral AIMistral AI
WeightsNo public weights listedNo public weights listed
ReleasedAugust 13, 2025April 30, 2026
Context window131K262K
Input $/Mtok$0.40$1.50
Output $/Mtok$2.00$7.50
Coding indexNot benchmarked25.5
Independent measurements behind it03
Cost per solved taskNot computable$6.02
SourceOpenRouter listingOpenRouter listing

Questions

Is Mistral Medium 3.1 better than Mistral Medium 3.5 for coding?

Only Mistral Medium 3.5 has a coding score, 25.5 on the Vibe Coding Index; Mistral Medium 3.1 has none, so the two cannot be ranked on coding. Mistral Medium 3.1 has the edge where output tokens cost 3.8x less, and where what matters is TaxEval (Vals AI) or MortgageTax (Vals AI), where it leads.

Which is cheaper, Mistral Medium 3.1 or Mistral Medium 3.5?

Mistral Medium 3.1 costs $0.40 per million input tokens and $2.00 per million output tokens; Mistral Medium 3.5 costs $1.50 and $7.50. Cost per solved task is known for Mistral Medium 3.5 only.

Which has the bigger context window, Mistral Medium 3.1 or Mistral Medium 3.5?

Mistral Medium 3.5, with 262K tokens against 131K.

How many benchmarks is the Mistral Medium 3.1 vs Mistral Medium 3.5 comparison based on?

60 benchmarks have a result for both models as of October 21, 2026. Mistral Medium 3.1's coding index rests on 0 independent benchmarks and Mistral Medium 3.5's on 3. Where only one model has a result, the page says so instead of naming a winner.

Compare next