Enter opens the highlighted result. Esc closes.

MiniMax M3 vs Mistral Medium 3.5

MiniMax M3 leads Mistral Medium 3.5 on coding, 39.2 to 25.5 on the Vibe Coding Index, and MiniMax M3 costs 6.3x less per output token ($1.20 vs $7.50 per million). Updated October 22, 2026; 79 benchmarks have a result for both.

Replace MiniMax M3 Replace Mistral Medium 3.5
MiniMax M3MiniMax
Coding
39.2
Overall
51.7
Output $/M
$1.20
71
Mistral Medium 3.5Mistral AI
Coding
25.5
Overall
37.3
Output $/M
$7.50
8
vs boards won of 79 shared

MiniMax M3 or Mistral Medium 3.5: which to pick

Pick MiniMax M3 for coding: it scores 39.2 on the Vibe Coding Index against 25.5 for Mistral Medium 3.5.

Pick Mistral Medium 3.5 for work measured by ALE-Bench or τ²-Bench Telecom, where it leads.

Model AMiniMax M3MiniMax39.2/1006 independent benchmarks$0.56 per solved taskModel BMistral Medium 3.5Mistral AI25.5/1003 independent benchmarks$6.02 per solved task
Shared results
79
MiniMax M3 only
37
Mistral Medium 3.5 only
2
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
MiniMax M3 39.2 from 6 benchmarks, Mistral Medium 3.5 25.5 from 3 benchmarks.
Widest category
Agentic work, 19.5 points apart on average over 6 shared benchmarks.
Widest single gap
GPQA Diamond: MiniMax M3 92.7% against Mistral Medium 3.5 34.9%, 57.8 points apart on a 0 to 100 scale.
Output price
MiniMax M3 $1.20 against Mistral Medium 3.5 $7.50 per million output tokens, 6.3x apart.
Context window
MiniMax M3 takes 1.05M 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
CategoryMiniMax M3BarsMistral Medium 3.5Ties
Coding121
Intelligence20
Agentic work51
Reasoning80
Math21
Knowledge81
Web design80
General264
All shared boards718
CodingLike-for-likeSix of these boards feed the Vibe Coding Index121
Coding benchmarks for MiniMax M3 and Mistral Medium 3.5
BenchmarkMiniMax M3Mistral Medium 3.5Leader
LiveBench coding70.9%Not measuredOnly MiniMax M3 measured
LMArena WebDev14821264MiniMax M3
AA Coding Index58.646.9MiniMax M3
LiveCodeBench (Vals AI)82.2%Not measuredOnly MiniMax M3 measured
SWE-bench Verified (Vals AI)75.0%66.4%MiniMax M3
Terminal-Bench 4 (Vals AI)1.0%Not measuredOnly MiniMax M3 measured
Vibe Code Bench (Vals AI)47.6%2.9%MiniMax M3
Code migration (Vals AI)19.9%5.1%MiniMax M3
Terminal-Bench 2.1 (Vals AI)53.6%39.0%MiniMax M3
SWE-bench Multimodal (Vals AI)33.3%Not measuredOnly MiniMax M3 measured
Vibe Code Bench 1-100 (Vals AI)9.2%Not measuredOnly MiniMax M3 measured
SkillsBench (Vals AI)51.5%Not measuredOnly MiniMax M3 measured
CyberBench (Vals AI)65.0%Not measuredOnly MiniMax M3 measured
SciCode47.1%40.2%MiniMax M3
Terminal-Bench Hard (Artificial Analysis run)42.4%33.3%MiniMax M3
FrontierCode14.7%Not measuredOnly MiniMax M3 measured
ALE-Bench640.0764.0Mistral Medium 3.5
LMArena Text: coding14701460MiniMax M3
LMArena Text: software and IT14661458MiniMax M3
LMArena WebDev: React14781254MiniMax M3
LMArena WebDev: HTML14551308MiniMax M3
LMArena WebDev: from an image1470Not measuredOnly MiniMax M3 measured
Neither model has a result on the other 17 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for MiniMax M3 and Mistral Medium 3.5
BenchmarkMiniMax M3Mistral Medium 3.5Leader
AA Intelligence Index29.214.2MiniMax M3
Epoch Capabilities Index146.9141.4MiniMax M3
Agentic workLike-for-likePublic boards, shown as published, kept out of the index51
Agentic work benchmarks for MiniMax M3 and Mistral Medium 3.5
BenchmarkMiniMax M3Mistral Medium 3.5Leader
AA Agentic Index29.57.0MiniMax M3
Design Arena: agents building web apps1200Not measuredOnly MiniMax M3 measured
Design Arena: agents building full-stack apps1197Not measuredOnly MiniMax M3 measured
Design Arena: agents building mobile apps1169Not measuredOnly MiniMax M3 measured
Design Arena: agents building Android apps1159Not measuredOnly MiniMax M3 measured
Design Arena: agents building games1158Not measuredOnly MiniMax M3 measured
Design Arena: HTML slides1130Not measuredOnly MiniMax M3 measured
Design Arena: PowerPoint slides1181Not measuredOnly MiniMax M3 measured
Design Arena: spreadsheets1028Not measuredOnly MiniMax M3 measured
LiveBench research68.0%Not measuredOnly MiniMax M3 measured
LiveBench browser8.0%Not measuredOnly MiniMax M3 measured
LiveBench long agentic12.4%Not measuredOnly MiniMax M3 measured
Finance Agent (Vals AI)48.3%32.1%MiniMax M3
Tax Agent Bench (Vals AI)20.6%4.5%MiniMax M3
Legal Research Bench (Vals AI)29.8%9.1%MiniMax M3
Excel Modeling Benchmark (Vals AI)47.8%11.2%MiniMax M3
τ²-Bench Telecom88.9%94.2%Mistral Medium 3.5
APEX-Agents37.7%Not measuredOnly MiniMax M3 measured
OSWorld 2.04.6%Not measuredOnly MiniMax M3 measured
Vending-Bench 2$2,158Not measuredOnly MiniMax M3 measured
Neither model has a result on the other 21 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index80
Reasoning benchmarks for MiniMax M3 and Mistral Medium 3.5
BenchmarkMiniMax M3Mistral Medium 3.5Leader
GPQA Diamond92.7%34.9%MiniMax M3
LiveBench reasoning74.5%Not measuredOnly MiniMax M3 measured
MMMU Pro (Vals AI)81.2%Not measuredOnly MiniMax M3 measured
GPQA Diamond (Artificial Analysis run)92.9%74.8%MiniMax M3
Humanity's Last Exam (Artificial Analysis run)39.0%13.8%MiniMax M3
GPQA Diamond (Epoch AI run)90.9%Not measuredOnly MiniMax M3 measured
SimpleBench45.8%Not measuredOnly MiniMax M3 measured
Chess puzzles13.0%Not measuredOnly MiniMax M3 measured
Mystery game puzzles8.0%Not measuredOnly MiniMax M3 measured
LMArena Text: hard prompts14471436MiniMax M3
LMArena Text: expert14611432MiniMax M3
LMArena Text: hard prompts in English14551445MiniMax M3
LMArena Vision: diagrams12661254MiniMax M3
LMArena Vision: homework12681230MiniMax M3
Kagi LLM BenchmarkNot measured41.4%Only Mistral Medium 3.5 measured
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index21
Math benchmarks for MiniMax M3 and Mistral Medium 3.5
BenchmarkMiniMax M3Mistral Medium 3.5Leader
OTIS Mock AIME71.1%Not measuredOnly MiniMax M3 measured
ProofBench18.0%9.0%MiniMax M3
LMArena Text: math14291431Mistral Medium 3.5
LMArena Text: mathematical work14481440MiniMax M3
Neither model has a result on the other 9 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index81
Knowledge benchmarks for MiniMax M3 and Mistral Medium 3.5
BenchmarkMiniMax M3Mistral Medium 3.5Leader
MMLU Pro84.2%75.3%MiniMax M3
LegalBench (Vals AI)85.4%Not measuredOnly MiniMax M3 measured
CaseLaw (Vals AI)Not measured44.2%Only Mistral Medium 3.5 measured
CorpFin (Vals AI)68.1%58.8%MiniMax M3
TaxEval (Vals AI)72.7%68.0%MiniMax M3
MortgageTax (Vals AI)68.4%28.9%MiniMax M3
MedCode (Vals AI)46.3%33.8%MiniMax M3
LMArena Text: science14521428MiniMax M3
LMArena Text: medicine and healthcare14411409MiniMax M3
LMArena Text: legal and government14371437Mistral Medium 3.5
LMArena Text: business and finance14341426MiniMax M3
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 MiniMax M3 and Mistral Medium 3.5
BenchmarkMiniMax M3Mistral Medium 3.5Leader
Design Arena: websites12571142MiniMax M3
Design Arena: UI components12421076MiniMax M3
Design Arena: game dev12101079MiniMax M3
Design Arena: data viz12361120MiniMax M3
Design Arena: 3D12081060MiniMax M3
Design Arena: all code categories12471121MiniMax M3
Design Arena: SVG1161949MiniMax M3
Design Arena: ASCII art11611062MiniMax M3
LiveBench design66.2%Not measuredOnly MiniMax M3 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index264
General benchmarks for MiniMax M3 and Mistral Medium 3.5
BenchmarkMiniMax M3Mistral Medium 3.5Leader
LiveBench data analysis76.2%Not measuredOnly MiniMax M3 measured
Public Benefits Bench (Vals AI)64.1%Not measuredOnly MiniMax M3 measured
SAGE (Vals AI)50.6%37.6%MiniMax M3
MedScribe (Vals AI)87.3%67.7%MiniMax M3
Vals Multimodal Index60.0%34.8%MiniMax M3
IFBench82.9%68.8%MiniMax M3
Long context reasoning (AA-LCR)83.0%69.3%MiniMax M3
DTBench78.9%75.5%MiniMax M3
LMCA33.7%26.1%MiniMax M3
Surface Evolver Bench55.0%26.9%MiniMax M3
LMArena Text14331421MiniMax M3
LMArena Text: instruction following14331415MiniMax M3
LMArena Text: creative writing14041374MiniMax M3
LMArena Vision12511222MiniMax M3
LMArena Text: English14431433MiniMax M3
LMArena Text: non-English14201404MiniMax M3
LMArena Text: Chinese14661444MiniMax M3
LMArena Text: German14281453Mistral Medium 3.5
LMArena Text: Japanese1380Not measuredOnly MiniMax M3 measured
LMArena Text: Korean13731384Mistral Medium 3.5
LMArena Text: French14441448Mistral Medium 3.5
LMArena Text: Spanish14331411MiniMax M3
LMArena Text: Russian14261395MiniMax M3
LMArena Text: Polish14231430Mistral Medium 3.5
LMArena Text: multi-turn14431423MiniMax M3
LMArena Text: longer queries14461415MiniMax M3
LMArena Text: writing and language14191384MiniMax M3
LMArena Text: entertainment and media14031382MiniMax M3
LMArena Vision: English12631240MiniMax M3
LMArena Vision: Chinese13111244MiniMax M3
LMArena Vision: reading text12591233MiniMax M3
LMArena Vision: humor12351216MiniMax M3
LMArena Vision: recognizing things1197Not measuredOnly MiniMax M3 measured
LMArena Vision: creative writing12341198MiniMax M3
LMArena Document1435Not measuredOnly MiniMax M3 measured
Neither model has a result on the other 11 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for MiniMax M3 and Mistral Medium 3.5
BenchmarkMiniMax M3Mistral 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

MiniMax M3$0.0009Fits in one request
Mistral Medium 3.5$0.0053Fits in one request

MiniMax M3 costs less

Repository review

50K input + 3K output tokens

MiniMax M3$0.019Fits in one request
Mistral Medium 3.5$0.098Fits in one request

MiniMax M3 costs less

Agent loop

200K input + 10K output tokens

MiniMax M3$0.072Fits in one request
Mistral Medium 3.5$0.375Fits in one request

MiniMax M3 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 MiniMax M3 and Mistral Medium 3.5
SpecificationMiniMax M3Mistral Medium 3.5
MakerMiniMaxMistral AI
WeightsOpen weightsNo public weights listed
ReleasedMay 31, 2026April 30, 2026
Context window1.05M262K
Input $/Mtok$0.30$1.50
Output $/Mtok$1.20$7.50
Coding index39.225.5
Independent measurements behind it63
Cost per solved task$0.56$6.02
SourceOpenRouter listingOpenRouter listing

Questions

Is MiniMax M3 better than Mistral Medium 3.5 for coding?

Pick MiniMax M3 for coding: it scores 39.2 on the Vibe Coding Index against 25.5 for Mistral Medium 3.5. Pick Mistral Medium 3.5 for work measured by ALE-Bench or τ²-Bench Telecom, where it leads.

Which is cheaper, MiniMax M3 or Mistral Medium 3.5?

MiniMax M3 costs $0.30 per million input tokens and $1.20 per million output tokens; Mistral Medium 3.5 costs $1.50 and $7.50. Per solved SWE-bench Verified task, MiniMax M3 costs $0.56 and Mistral Medium 3.5 $6.02.

Which has the bigger context window, MiniMax M3 or Mistral Medium 3.5?

MiniMax M3, with 1.05M tokens against 262K.

How many benchmarks is the MiniMax M3 vs Mistral Medium 3.5 comparison based on?

79 benchmarks have a result for both models as of October 22, 2026. MiniMax M3's coding index rests on 6 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

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/minimax-minimax-m3-vs-mistral-medium-3-5" title="MiniMax M3 vs Mistral Medium 3.5, 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/minimax-minimax-m3-vs-mistral-medium-3-5">LLMBenchmark.ai, MiniMax M3 vs Mistral Medium 3.5</a></p>