Enter opens the highlighted result. Esc closes.

Mistral Medium 3.5 vs Qwen3.5-27B

Qwen3.5-27B leads Mistral Medium 3.5 on the Artificial Analysis Intelligence Index, 22.9 to 14.2, and Qwen3.5-27B costs 4.8x less per output token ($1.56 vs $7.50 per million). Updated October 22, 2026; 48 benchmarks have a result for both.

Replace Mistral Medium 3.5 Replace Qwen3.5-27B
Mistral Medium 3.5Mistral AI
Coding
25.5
Overall
37.3
Output $/M
$7.50
28
Qwen3.5-27BQwen
Coding
No data
Overall
No data
Output $/M
$1.56
20
vs boards won of 48 shared

Mistral Medium 3.5 or Qwen3.5-27B: which to pick

Only Mistral Medium 3.5 has a coding score, 25.5 on the Vibe Coding Index; Qwen3.5-27B has none, so the two cannot be ranked on coding.

Pick Qwen3.5-27B for output tokens 4.8x cheaper ($1.56 vs $7.50 per million) and work measured by LMArena WebDev or LMArena WebDev: React, where it leads.

Model AMistral Medium 3.5Mistral AI25.5/1003 independent benchmarks$6.02 per solved taskModel BQwen3.5-27BQwenNot benchmarked1 independent benchmarkNo cost per solved task
Shared results
48
Mistral Medium 3.5 only
33
Qwen3.5-27B only
5
Like-for-like categories
7 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, Qwen3.5-27B not benchmarked.
Widest category
Coding, 9.5 points apart on average over 7 shared benchmarks.
Widest single gap
LMArena WebDev: React: Mistral Medium 3.5 1254 against Qwen3.5-27B 1346, 15.3 points apart on a 0 to 100 scale.
Output price
Mistral Medium 3.5 $7.50 against Qwen3.5-27B $1.56 per million output tokens, 4.8x apart.
Context window
Both take 262K tokens.

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 3.5BarsQwen3.5-27BTies
Coding43
Intelligence01
Agentic work10
Reasoning43
Math20
Knowledge22
General1511
All shared boards2820
CodingLike-for-likeSix of these boards feed the Vibe Coding Index43
Coding benchmarks for Mistral Medium 3.5 and Qwen3.5-27B
BenchmarkMistral Medium 3.5Qwen3.5-27BLeader
LMArena WebDev12641358Qwen3.5-27B
AA Coding Index46.9Not measuredOnly Mistral Medium 3.5 measured
SWE-bench Verified (Vals AI)66.4%Not measuredOnly Mistral Medium 3.5 measured
Vibe Code Bench (Vals AI)2.9%Not measuredOnly Mistral Medium 3.5 measured
Code migration (Vals AI)5.1%Not measuredOnly Mistral Medium 3.5 measured
Terminal-Bench 2.1 (Vals AI)39.0%Not measuredOnly Mistral Medium 3.5 measured
SciCode40.2%Not measuredOnly Mistral Medium 3.5 measured
Terminal-Bench Hard (Artificial Analysis run)33.3%32.6%Mistral Medium 3.5
WeirdMLNot measured39.5%Only Qwen3.5-27B measured
ALE-Bench764.0349.4Mistral Medium 3.5
LMArena Text: coding14601427Mistral Medium 3.5
LMArena Text: software and IT14581431Mistral Medium 3.5
LMArena WebDev: React12541346Qwen3.5-27B
LMArena WebDev: HTML13081386Qwen3.5-27B
Neither model has a result on the other 25 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Mistral Medium 3.5 and Qwen3.5-27B
BenchmarkMistral Medium 3.5Qwen3.5-27BLeader
AA Intelligence Index14.222.9Qwen3.5-27B
Epoch Capabilities Index141.4Not measuredOnly Mistral Medium 3.5 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for Mistral Medium 3.5 and Qwen3.5-27B
BenchmarkMistral Medium 3.5Qwen3.5-27BLeader
AA Agentic Index7.0Not measuredOnly Mistral Medium 3.5 measured
Finance Agent (Vals AI)32.1%Not measuredOnly Mistral Medium 3.5 measured
Tax Agent Bench (Vals AI)4.5%Not measuredOnly Mistral Medium 3.5 measured
Legal Research Bench (Vals AI)9.1%Not measuredOnly Mistral Medium 3.5 measured
Excel Modeling Benchmark (Vals AI)11.2%Not measuredOnly Mistral Medium 3.5 measured
τ²-Bench Telecom94.2%93.9%Mistral Medium 3.5
Vending-Bench 2Not measured$202Only Qwen3.5-27B measured
Neither model has a result on the other 34 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index43
Reasoning benchmarks for Mistral Medium 3.5 and Qwen3.5-27B
BenchmarkMistral Medium 3.5Qwen3.5-27BLeader
GPQA Diamond34.9%Not measuredOnly Mistral Medium 3.5 measured
GPQA Diamond (Artificial Analysis run)74.8%85.8%Qwen3.5-27B
Humanity's Last Exam (Artificial Analysis run)13.8%23.9%Qwen3.5-27B
LMArena Text: hard prompts14361415Mistral Medium 3.5
LMArena Text: expert14321427Mistral Medium 3.5
LMArena Text: hard prompts in English14451429Mistral Medium 3.5
LMArena Vision: diagrams12541249Mistral Medium 3.5
LMArena Vision: homework12301256Qwen3.5-27B
Kagi LLM Benchmark41.4%Not measuredOnly Mistral Medium 3.5 measured
Neither model has a result on the other 13 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index20
Math benchmarks for Mistral Medium 3.5 and Qwen3.5-27B
BenchmarkMistral Medium 3.5Qwen3.5-27BLeader
ProofBench9.0%Not measuredOnly Mistral Medium 3.5 measured
LMArena Text: math14311429Mistral Medium 3.5
LMArena Text: mathematical work14401429Mistral Medium 3.5
Neither model has a result on the other 10 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index22
Knowledge benchmarks for Mistral Medium 3.5 and Qwen3.5-27B
BenchmarkMistral Medium 3.5Qwen3.5-27BLeader
MMLU Pro75.3%Not measuredOnly Mistral Medium 3.5 measured
CaseLaw (Vals AI)44.2%Not measuredOnly Mistral Medium 3.5 measured
CorpFin (Vals AI)58.8%Not measuredOnly Mistral Medium 3.5 measured
TaxEval (Vals AI)68.0%Not measuredOnly Mistral Medium 3.5 measured
MortgageTax (Vals AI)28.9%Not measuredOnly Mistral Medium 3.5 measured
MedCode (Vals AI)33.8%Not measuredOnly Mistral Medium 3.5 measured
LMArena Text: science14281437Qwen3.5-27B
LMArena Text: medicine and healthcare14091425Qwen3.5-27B
LMArena Text: legal and government14371405Mistral Medium 3.5
LMArena Text: business and finance14261399Mistral Medium 3.5
Neither model has a result on the other 8 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for Mistral Medium 3.5 and Qwen3.5-27B
BenchmarkMistral Medium 3.5Qwen3.5-27BLeader
Design Arena: websites1142Not measuredOnly Mistral Medium 3.5 measured
Design Arena: UI components1076Not measuredOnly Mistral Medium 3.5 measured
Design Arena: game dev1079Not measuredOnly Mistral Medium 3.5 measured
Design Arena: data viz1121Not measuredOnly Mistral Medium 3.5 measured
Design Arena: 3D1060Not measuredOnly Mistral Medium 3.5 measured
Design Arena: all code categories1121Not measuredOnly Mistral Medium 3.5 measured
Design Arena: SVG949Not measuredOnly Mistral Medium 3.5 measured
Design Arena: ASCII art1062Not measuredOnly Mistral Medium 3.5 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index1511
General benchmarks for Mistral Medium 3.5 and Qwen3.5-27B
BenchmarkMistral Medium 3.5Qwen3.5-27BLeader
SAGE (Vals AI)37.6%Not measuredOnly Mistral Medium 3.5 measured
MedScribe (Vals AI)67.7%Not measuredOnly Mistral Medium 3.5 measured
Vals Multimodal Index34.8%Not measuredOnly Mistral Medium 3.5 measured
IFBench68.8%75.6%Qwen3.5-27B
Long context reasoning (AA-LCR)69.3%77.7%Qwen3.5-27B
DTBench75.5%82.4%Qwen3.5-27B
LMCA26.1%34.0%Qwen3.5-27B
Surface Evolver Bench26.9%Not measuredOnly Mistral Medium 3.5 measured
LMArena Text14211409Mistral Medium 3.5
LMArena Text: instruction following14151393Mistral Medium 3.5
LMArena Text: creative writing13741362Mistral Medium 3.5
LMArena Vision12221241Qwen3.5-27B
LMArena Text: English14331425Mistral Medium 3.5
LMArena Text: non-English14041390Mistral Medium 3.5
LMArena Text: Chinese14441478Qwen3.5-27B
LMArena Text: German14531392Mistral Medium 3.5
LMArena Text: JapaneseNot measured1346Only Qwen3.5-27B measured
LMArena Text: Korean13841359Mistral Medium 3.5
LMArena Text: French14481410Mistral Medium 3.5
LMArena Text: Spanish14111407Mistral Medium 3.5
LMArena Text: Russian13951390Mistral Medium 3.5
LMArena Text: Polish14301375Mistral Medium 3.5
LMArena Text: multi-turn14231410Mistral Medium 3.5
LMArena Text: longer queries14151413Mistral Medium 3.5
LMArena Text: writing and language13841380Mistral Medium 3.5
LMArena Text: entertainment and media13821363Mistral Medium 3.5
LMArena Vision: English12401246Qwen3.5-27B
LMArena Vision: Chinese12441301Qwen3.5-27B
LMArena Vision: reading text12331246Qwen3.5-27B
LMArena Vision: humor12161227Qwen3.5-27B
LMArena Vision: captioningNot measured1170Only Qwen3.5-27B measured
LMArena Vision: recognizing thingsNot measured1210Only Qwen3.5-27B measured
LMArena Vision: creative writing11981224Qwen3.5-27B
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 3.5 and Qwen3.5-27B
BenchmarkMistral Medium 3.5Qwen3.5-27BLeader
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
Qwen3.5-27B$0.0010Fits in one request

Qwen3.5-27B costs less

Repository review

50K input + 3K output tokens

Mistral Medium 3.5$0.098Fits in one request
Qwen3.5-27B$0.014Fits in one request

Qwen3.5-27B costs less

Agent loop

200K input + 10K output tokens

Mistral Medium 3.5$0.375Fits in one request
Qwen3.5-27B$0.055Fits in one request

Qwen3.5-27B 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 Qwen3.5-27B
SpecificationMistral Medium 3.5Qwen3.5-27B
MakerMistral AIQwen
WeightsNo public weights listedOpen weights
ReleasedApril 30, 2026February 25, 2026
Context window262K262K
Input $/Mtok$1.50$0.195
Output $/Mtok$7.50$1.56
Coding index25.5Not benchmarked
Independent measurements behind it31
Cost per solved task$6.02Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Mistral Medium 3.5 better than Qwen3.5-27B for coding?

Only Mistral Medium 3.5 has a coding score, 25.5 on the Vibe Coding Index; Qwen3.5-27B has none, so the two cannot be ranked on coding. Pick Qwen3.5-27B for output tokens 4.8x cheaper ($1.56 vs $7.50 per million) and work measured by LMArena WebDev or LMArena WebDev: React, where it leads.

Which is cheaper, Mistral Medium 3.5 or Qwen3.5-27B?

Mistral Medium 3.5 costs $1.50 per million input tokens and $7.50 per million output tokens; Qwen3.5-27B costs $0.195 and $1.56. Cost per solved task is known for Mistral Medium 3.5 only.

Which has the bigger context window, Mistral Medium 3.5 or Qwen3.5-27B?

Neither: both take 262K tokens.

How many benchmarks is the Mistral Medium 3.5 vs Qwen3.5-27B comparison based on?

48 benchmarks have a result for both models as of October 22, 2026. Mistral Medium 3.5's coding index rests on 3 independent benchmarks and Qwen3.5-27B's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next