Enter opens the highlighted result. Esc closes.

Mistral Medium 3.5 vs Qwen3.6 Plus

Qwen3.6 Plus leads Mistral Medium 3.5 on coding, 44.1 to 25.5 on the Vibe Coding Index, and Qwen3.6 Plus costs 3.8x less per output token ($1.95 vs $7.50 per million). Updated October 21, 2026; 68 benchmarks have a result for both.

Replace Mistral Medium 3.5 Replace Qwen3.6 Plus
Mistral Medium 3.5Mistral AI
Coding
25.5
Overall
37.3
Output $/M
$7.50
4
Qwen3.6 PlusQwen
Coding
44.1
Overall
56.2
Output $/M
$1.95
64
vs boards won of 68 shared

Mistral Medium 3.5 or Qwen3.6 Plus: which to pick

Pick Qwen3.6 Plus for coding: it scores 44.1 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 LMArena Text: legal and government, where it leads.

Model AMistral Medium 3.5Mistral AI25.5/1003 independent benchmarks$6.02 per solved taskModel BQwen3.6 PlusQwen44.1/1003 independent benchmarks$1.19 per solved task
Shared results
68
Mistral Medium 3.5 only
13
Qwen3.6 Plus only
15
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
Mistral Medium 3.5 25.5 from 3 benchmarks, Qwen3.6 Plus 44.1 from 3 benchmarks.
Widest category
Web design, 15.8 points apart on average over 8 shared benchmarks.
Widest single gap
GPQA Diamond: Mistral Medium 3.5 34.9% against Qwen3.6 Plus 87.4%, 52.5 points apart on a 0 to 100 scale.
Output price
Mistral Medium 3.5 $7.50 against Qwen3.6 Plus $1.95 per million output tokens, 3.8x apart.
Context window
Mistral Medium 3.5 takes 262K tokens, Qwen3.6 Plus 1M.

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 3.5BarsQwen3.6 PlusTies
Coding111
Intelligence02
Agentic work05
Reasoning06
Math02
Knowledge19
Web design08
General221
All shared boards464
CodingLike-for-likeSix of these boards feed the Vibe Coding Index111
Coding benchmarks for Mistral Medium 3.5 and Qwen3.6 Plus
BenchmarkMistral Medium 3.5Qwen3.6 PlusLeader
LMArena WebDev12641461Qwen3.6 Plus
AA Coding Index46.954.5Qwen3.6 Plus
LiveCodeBench (Vals AI)Not measured86.0%Only Qwen3.6 Plus measured
SWE-bench Verified (Vals AI)66.4%73.4%Qwen3.6 Plus
Vibe Code Bench (Vals AI)2.9%25.6%Qwen3.6 Plus
Code migration (Vals AI)5.1%11.1%Qwen3.6 Plus
ProgramBench (Vals AI)Not measured0.0%Only Qwen3.6 Plus measured
Terminal-Bench 2.1 (Vals AI)39.0%53.2%Qwen3.6 Plus
SciCode40.2%Not measuredOnly Mistral Medium 3.5 measured
Terminal-Bench Hard (Artificial Analysis run)33.3%43.9%Qwen3.6 Plus
ALE-Bench764.0670.1Mistral Medium 3.5
LMArena Text: coding14601467Qwen3.6 Plus
LMArena Text: software and IT14581462Qwen3.6 Plus
LMArena WebDev: React12541454Qwen3.6 Plus
LMArena WebDev: HTML13081463Qwen3.6 Plus
LMArena WebDev: from an imageNot measured1472Only Qwen3.6 Plus measured
Neither model has a result on the other 23 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Mistral Medium 3.5 and Qwen3.6 Plus
BenchmarkMistral Medium 3.5Qwen3.6 PlusLeader
AA Intelligence Index14.227.0Qwen3.6 Plus
Epoch Capabilities Index141.4147.3Qwen3.6 Plus
Agentic workLike-for-likePublic boards, shown as published, kept out of the index05
Agentic work benchmarks for Mistral Medium 3.5 and Qwen3.6 Plus
BenchmarkMistral Medium 3.5Qwen3.6 PlusLeader
AA Agentic Index7.0Not measuredOnly Mistral Medium 3.5 measured
Finance Agent (Vals AI)32.1%40.9%Qwen3.6 Plus
Tax Agent Bench (Vals AI)4.5%7.7%Qwen3.6 Plus
Legal Research Bench (Vals AI)9.1%14.9%Qwen3.6 Plus
Excel Modeling Benchmark (Vals AI)11.2%32.9%Qwen3.6 Plus
τ²-Bench Telecom94.2%97.7%Qwen3.6 Plus
Vending-Bench 2Not measured$5,115Only Qwen3.6 Plus measured
Neither model has a result on the other 34 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index06
Reasoning benchmarks for Mistral Medium 3.5 and Qwen3.6 Plus
BenchmarkMistral Medium 3.5Qwen3.6 PlusLeader
GPQA Diamond34.9%87.4%Qwen3.6 Plus
MMMU Pro (Vals AI)Not measured84.2%Only Qwen3.6 Plus measured
GPQA Diamond (Artificial Analysis run)74.8%88.2%Qwen3.6 Plus
Humanity's Last Exam (Artificial Analysis run)13.8%27.8%Qwen3.6 Plus
GPQA Diamond (Epoch AI run)Not measured88.4%Only Qwen3.6 Plus measured
Chess puzzlesNot measured14.0%Only Qwen3.6 Plus measured
Mystery game puzzlesNot measured12.0%Only Qwen3.6 Plus measured
LMArena Text: hard prompts14361448Qwen3.6 Plus
LMArena Text: expert14321454Qwen3.6 Plus
LMArena Text: hard prompts in English14451455Qwen3.6 Plus
LMArena Vision: diagrams1254Not measuredOnly Mistral Medium 3.5 measured
LMArena Vision: homework1230Not measuredOnly Mistral Medium 3.5 measured
Kagi LLM Benchmark41.4%Not measuredOnly Mistral Medium 3.5 measured
Neither model has a result on the other 9 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for Mistral Medium 3.5 and Qwen3.6 Plus
BenchmarkMistral Medium 3.5Qwen3.6 PlusLeader
AIMENot measured94.6%Only Qwen3.6 Plus measured
OTIS Mock AIMENot measured93.3%Only Qwen3.6 Plus measured
FrontierMath, tiers 1 to 3Not measured38.2%Only Qwen3.6 Plus measured
ProofBench9.0%Not measuredOnly Mistral Medium 3.5 measured
LMArena Text: math14311449Qwen3.6 Plus
LMArena Text: mathematical work14401448Qwen3.6 Plus
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index19
Knowledge benchmarks for Mistral Medium 3.5 and Qwen3.6 Plus
BenchmarkMistral Medium 3.5Qwen3.6 PlusLeader
MMLU Pro75.3%87.7%Qwen3.6 Plus
LegalBench (Vals AI)Not measured84.2%Only Qwen3.6 Plus measured
CaseLaw (Vals AI)44.2%51.5%Qwen3.6 Plus
CorpFin (Vals AI)58.8%61.9%Qwen3.6 Plus
TaxEval (Vals AI)68.0%74.7%Qwen3.6 Plus
MortgageTax (Vals AI)28.9%68.0%Qwen3.6 Plus
MedCode (Vals AI)33.8%36.9%Qwen3.6 Plus
SimpleQA VerifiedNot measured44.1%Only Qwen3.6 Plus measured
LMArena Text: science14281439Qwen3.6 Plus
LMArena Text: medicine and healthcare14091442Qwen3.6 Plus
LMArena Text: legal and government14371437Mistral Medium 3.5
LMArena Text: business and finance14261430Qwen3.6 Plus
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index08
Web design benchmarks for Mistral Medium 3.5 and Qwen3.6 Plus
BenchmarkMistral Medium 3.5Qwen3.6 PlusLeader
Design Arena: websites11421243Qwen3.6 Plus
Design Arena: UI components10791233Qwen3.6 Plus
Design Arena: game dev10791211Qwen3.6 Plus
Design Arena: data viz11201228Qwen3.6 Plus
Design Arena: 3D10611202Qwen3.6 Plus
Design Arena: all code categories11211236Qwen3.6 Plus
Design Arena: SVG9501161Qwen3.6 Plus
Design Arena: ASCII art10631113Qwen3.6 Plus
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index221
General benchmarks for Mistral Medium 3.5 and Qwen3.6 Plus
BenchmarkMistral Medium 3.5Qwen3.6 PlusLeader
SAGE (Vals AI)37.6%44.9%Qwen3.6 Plus
MedScribe (Vals AI)67.7%77.0%Qwen3.6 Plus
Vals Multimodal Index34.8%51.5%Qwen3.6 Plus
IFBench68.8%75.2%Qwen3.6 Plus
Long context reasoning (AA-LCR)69.3%78.3%Qwen3.6 Plus
DTBench75.5%81.9%Qwen3.6 Plus
LMCA26.1%33.1%Qwen3.6 Plus
CL-benchNot measured20.3%Only Qwen3.6 Plus measured
Surface Evolver Bench26.9%Not measuredOnly Mistral Medium 3.5 measured
LMArena Text14211436Qwen3.6 Plus
LMArena Text: instruction following14151424Qwen3.6 Plus
LMArena Text: creative writing13741404Qwen3.6 Plus
LMArena Vision1222Not measuredOnly Mistral Medium 3.5 measured
LMArena Text: English14331445Qwen3.6 Plus
LMArena Text: non-English14041424Qwen3.6 Plus
LMArena Text: Chinese14441477Qwen3.6 Plus
LMArena Text: German14531451Mistral Medium 3.5
LMArena Text: JapaneseNot measured1390Only Qwen3.6 Plus measured
LMArena Text: Korean13841379Mistral Medium 3.5
LMArena Text: French14481455Qwen3.6 Plus
LMArena Text: Spanish14111432Qwen3.6 Plus
LMArena Text: Russian13951434Qwen3.6 Plus
LMArena Text: Polish14301433Qwen3.6 Plus
LMArena Text: multi-turn14231438Qwen3.6 Plus
LMArena Text: longer queries14151439Qwen3.6 Plus
LMArena Text: writing and language13841418Qwen3.6 Plus
LMArena Text: entertainment and media13821402Qwen3.6 Plus
LMArena Vision: English1240Not measuredOnly Mistral Medium 3.5 measured
LMArena Vision: Chinese1244Not measuredOnly Mistral Medium 3.5 measured
LMArena Vision: reading text1233Not measuredOnly Mistral Medium 3.5 measured
LMArena Vision: humor1216Not measuredOnly Mistral Medium 3.5 measured
LMArena Vision: creative writing1198Not measuredOnly Mistral Medium 3.5 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 Mistral Medium 3.5 and Qwen3.6 Plus
BenchmarkMistral Medium 3.5Qwen3.6 PlusLeader
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 3.5$0.0053Fits in one request
Qwen3.6 Plus$0.0013Fits in one request

Qwen3.6 Plus costs less

Repository review

50K input + 3K output tokens

Mistral Medium 3.5$0.098Fits in one request
Qwen3.6 Plus$0.022Fits in one request

Qwen3.6 Plus costs less

Agent loop

200K input + 10K output tokens

Mistral Medium 3.5$0.375Fits in one request
Qwen3.6 Plus$0.085Fits in one request

Qwen3.6 Plus 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 3.5 and Qwen3.6 Plus
SpecificationMistral Medium 3.5Qwen3.6 Plus
MakerMistral AIQwen
WeightsNo public weights listedNo public weights listed
ReleasedApril 30, 2026April 2, 2026
Context window262K1M
Input $/Mtok$1.50$0.325
Output $/Mtok$7.50$1.95
Coding index25.544.1
Independent measurements behind it33
Cost per solved task$6.02$1.19
SourceOpenRouter listingOpenRouter listing

Questions

Is Mistral Medium 3.5 better than Qwen3.6 Plus for coding?

Pick Qwen3.6 Plus for coding: it scores 44.1 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 LMArena Text: legal and government, where it leads.

Which is cheaper, Mistral Medium 3.5 or Qwen3.6 Plus?

Mistral Medium 3.5 costs $1.50 per million input tokens and $7.50 per million output tokens; Qwen3.6 Plus costs $0.325 and $1.95. Per solved SWE-bench Verified task, Mistral Medium 3.5 costs $6.02 and Qwen3.6 Plus $1.19.

Which has the bigger context window, Mistral Medium 3.5 or Qwen3.6 Plus?

Qwen3.6 Plus, with 1M tokens against 262K.

How many benchmarks is the Mistral Medium 3.5 vs Qwen3.6 Plus comparison based on?

68 benchmarks have a result for both models as of October 21, 2026. Mistral Medium 3.5's coding index rests on 3 independent benchmarks and Qwen3.6 Plus'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/mistral-medium-3-5-vs-qwen3-6-plus" title="Mistral Medium 3.5 vs Qwen3.6 Plus, 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/mistral-medium-3-5-vs-qwen3-6-plus">LLMBenchmark.ai, Mistral Medium 3.5 vs Qwen3.6 Plus</a></p>