Enter opens the highlighted result. Esc closes.

Mistral Large 4 vs Qwen3.5 397B A17B

Mistral Large 4 leads Qwen3.5 397B A17B on the Artificial Analysis Intelligence Index, 38.4 to 21.4, and Qwen3.5 397B A17B costs 1.8x less per output token ($2.34 vs $4.18 per million). Updated October 22, 2026; 51 benchmarks have a result for both.

Replace Mistral Large 4 Replace Qwen3.5 397B A17B
Mistral Large 4Mistral AI
Coding
56.4
Overall
54.6
Output $/M
$4.18
31
Qwen3.5 397B A17BQwen
Coding
No data
Overall
57.1
Output $/M
$2.34
20
vs boards won of 51 shared

Mistral Large 4 or Qwen3.5 397B A17B: which to pick

Only Mistral Large 4 has a coding score, 56.4 on the Vibe Coding Index; Qwen3.5 397B A17B has none, so the two cannot be ranked on coding.

Pick Qwen3.5 397B A17B for output tokens 1.8x cheaper ($2.34 vs $4.18 per million) and work measured by Mystery game puzzles or LMArena Text: hard prompts, where it leads.

Model AMistral Large 4Mistral AI56.4/1005 independent benchmarksNo cost per solved taskModel BQwen3.5 397B A17BQwenNot benchmarked1 independent benchmarkNo cost per solved task
Shared results
51
Mistral Large 4 only
30
Qwen3.5 397B A17B only
14
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 Large 4 56.4 from 5 benchmarks, Qwen3.5 397B A17B not benchmarked.
Widest category
Coding, 13.4 points apart on average over 7 shared benchmarks.
Widest single gap
LMArena WebDev: React: Mistral Large 4 1559 against Qwen3.5 397B A17B 1388, 28.5 points apart on a 0 to 100 scale.
Output price
Mistral Large 4 $4.18 against Qwen3.5 397B A17B $2.34 per million output tokens, 1.8x apart.
Context window
Mistral Large 4 takes 1.05M tokens, Qwen3.5 397B A17B 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 Large 4BarsQwen3.5 397B A17BTies
Coding70
Intelligence20
Reasoning34
Math40
Knowledge13
Web design70
General713
All shared boards3120
CodingLike-for-likeSix of these boards feed the Vibe Coding Index70
Coding benchmarks for Mistral Large 4 and Qwen3.5 397B A17B
BenchmarkMistral Large 4Qwen3.5 397B A17BLeader
LiveBench coding60.0%Not measuredOnly Mistral Large 4 measured
LMArena WebDev15431400Mistral Large 4
Terminal-Bench 4 (Vals AI)27.8%Not measuredOnly Mistral Large 4 measured
Vibe Code Bench (Vals AI)78.4%Not measuredOnly Mistral Large 4 measured
Code migration (Vals AI)30.6%Not measuredOnly Mistral Large 4 measured
IOI (Vals AI)45.3%Not measuredOnly Mistral Large 4 measured
SWE-bench Multimodal (Vals AI)33.1%Not measuredOnly Mistral Large 4 measured
Vibe Code Bench 1-100 (Vals AI)14.3%Not measuredOnly Mistral Large 4 measured
SciCode54.2%44.8%Mistral Large 4
Terminal-Bench Hard (Artificial Analysis run)Not measured40.9%Only Qwen3.5 397B A17B measured
FrontierCode39.4%Not measuredOnly Mistral Large 4 measured
ALE-Bench1213.2621.9Mistral Large 4
LMArena Text: coding14781464Mistral Large 4
LMArena Text: software and IT14671463Mistral Large 4
LMArena WebDev: React15591388Mistral Large 4
LMArena WebDev: HTML14871410Mistral Large 4
Neither model has a result on the other 23 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Mistral Large 4 and Qwen3.5 397B A17B
BenchmarkMistral Large 4Qwen3.5 397B A17BLeader
AA Intelligence Index38.421.4Mistral Large 4
Epoch Capabilities Index150.0146.8Mistral Large 4
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index11 boards, none shared
Agentic work benchmarks for Mistral Large 4 and Qwen3.5 397B A17B
BenchmarkMistral Large 4Qwen3.5 397B A17BLeader
LiveBench research28.1%Not measuredOnly Mistral Large 4 measured
LiveBench browser8.0%Not measuredOnly Mistral Large 4 measured
LiveBench long agentic11.8%Not measuredOnly Mistral Large 4 measured
Finance Agent (Vals AI)54.7%Not measuredOnly Mistral Large 4 measured
Tax Agent Bench (Vals AI)30.4%Not measuredOnly Mistral Large 4 measured
Legal Research Bench (Vals AI)31.7%Not measuredOnly Mistral Large 4 measured
Harvey's Legal Agent Benchmark (Vals AI)17.5%Not measuredOnly Mistral Large 4 measured
Excel Modeling Benchmark (Vals AI)56.2%Not measuredOnly Mistral Large 4 measured
BioMysteryBench (Vals AI)67.0%Not measuredOnly Mistral Large 4 measured
τ²-Bench TelecomNot measured95.6%Only Qwen3.5 397B A17B measured
APEX-AgentsNot measured24.9%Only Qwen3.5 397B A17B measured
Neither model has a result on the other 30 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index34
Reasoning benchmarks for Mistral Large 4 and Qwen3.5 397B A17B
BenchmarkMistral Large 4Qwen3.5 397B A17BLeader
LiveBench reasoning83.9%Not measuredOnly Mistral Large 4 measured
MysteryMechanism (Vals AI)12.2%Not measuredOnly Mistral Large 4 measured
GPQA Diamond (Artificial Analysis run)Not measured89.3%Only Qwen3.5 397B A17B measured
Humanity's Last Exam (Artificial Analysis run)35.0%29.0%Mistral Large 4
GPQA Diamond (Epoch AI run)88.1%86.4%Mistral Large 4
Chess puzzles33.0%Not measuredOnly Mistral Large 4 measured
Mystery game puzzles17.0%18.0%Qwen3.5 397B A17B
LMArena Text: hard prompts14441448Qwen3.5 397B A17B
LMArena Text: expert14441462Qwen3.5 397B A17B
LMArena Text: hard prompts in English14421450Qwen3.5 397B A17B
LMArena Vision: diagrams12881277Mistral Large 4
LMArena Vision: homeworkNot measured1292Only Qwen3.5 397B A17B measured
Neither model has a result on the other 10 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index40
Math benchmarks for Mistral Large 4 and Qwen3.5 397B A17B
BenchmarkMistral Large 4Qwen3.5 397B A17BLeader
OTIS Mock AIME98.3%88.9%Mistral Large 4
FrontierMath, tiers 1 to 358.6%31.2%Mistral Large 4
FrontierMath, tier 426.8%Not measuredOnly Mistral Large 4 measured
ProofBench10.0%Not measuredOnly Mistral Large 4 measured
LMArena Text: math14691453Mistral Large 4
LMArena Text: mathematical work14621454Mistral Large 4
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index13
Knowledge benchmarks for Mistral Large 4 and Qwen3.5 397B A17B
BenchmarkMistral Large 4Qwen3.5 397B A17BLeader
MedCode (Vals AI)40.7%Not measuredOnly Mistral Large 4 measured
SimpleQA Verified20.0%Not measuredOnly Mistral Large 4 measured
LMArena Text: science14481457Qwen3.5 397B A17B
LMArena Text: medicine and healthcare14331455Qwen3.5 397B A17B
LMArena Text: legal and government14251441Qwen3.5 397B A17B
LMArena Text: business and finance14391435Mistral Large 4
Neither model has a result on the other 12 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index70
Web design benchmarks for Mistral Large 4 and Qwen3.5 397B A17B
BenchmarkMistral Large 4Qwen3.5 397B A17BLeader
Design Arena: websites12581190Mistral Large 4
Design Arena: UI components12731161Mistral Large 4
Design Arena: game dev12251140Mistral Large 4
Design Arena: data viz12751175Mistral Large 4
Design Arena: 3D12521160Mistral Large 4
Design Arena: all code categories12591179Mistral Large 4
Design Arena: SVG12321139Mistral Large 4
Design Arena: ASCII art1202Not measuredOnly Mistral Large 4 measured
LiveBench design65.6%Not measuredOnly Mistral Large 4 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index713
General benchmarks for Mistral Large 4 and Qwen3.5 397B A17B
BenchmarkMistral Large 4Qwen3.5 397B A17BLeader
LiveBench data analysis76.5%Not measuredOnly Mistral Large 4 measured
MedScribe (Vals AI)80.4%Not measuredOnly Mistral Large 4 measured
IFBenchNot measured78.8%Only Qwen3.5 397B A17B measured
Long context reasoning (AA-LCR)81.3%77.3%Mistral Large 4
DTBench88.2%87.5%Mistral Large 4
LMCA35.8%37.9%Qwen3.5 397B A17B
Surface Evolver Bench28.1%Not measuredOnly Mistral Large 4 measured
Furniture assembly20.8%Not measuredOnly Mistral Large 4 measured
LMArena Text14311437Qwen3.5 397B A17B
LMArena Text: instruction following14221424Qwen3.5 397B A17B
LMArena Text: creative writing13631402Qwen3.5 397B A17B
LMArena Vision12721262Mistral Large 4
LMArena Text: English14331443Qwen3.5 397B A17B
LMArena Text: non-English14221430Qwen3.5 397B A17B
LMArena Text: Chinese14921498Qwen3.5 397B A17B
LMArena Text: GermanNot measured1445Only Qwen3.5 397B A17B measured
LMArena Text: Japanese14151429Qwen3.5 397B A17B
LMArena Text: KoreanNot measured1384Only Qwen3.5 397B A17B measured
LMArena Text: French14921462Mistral Large 4
LMArena Text: Spanish14551441Mistral Large 4
LMArena Text: Russian14171430Qwen3.5 397B A17B
LMArena Text: PolishNot measured1447Only Qwen3.5 397B A17B measured
LMArena Text: multi-turn14351446Qwen3.5 397B A17B
LMArena Text: longer queries14281441Qwen3.5 397B A17B
LMArena Text: writing and language13861415Qwen3.5 397B A17B
LMArena Text: entertainment and media13781399Qwen3.5 397B A17B
LMArena Vision: English12831268Mistral Large 4
LMArena Vision: ChineseNot measured1314Only Qwen3.5 397B A17B measured
LMArena Vision: reading text12841271Mistral Large 4
LMArena Vision: humorNot measured1262Only Qwen3.5 397B A17B measured
LMArena Vision: captioningNot measured1230Only Qwen3.5 397B A17B measured
LMArena Vision: recognizing thingsNot measured1265Only Qwen3.5 397B A17B measured
LMArena Vision: creative writingNot measured1260Only Qwen3.5 397B A17B measured
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 Large 4 and Qwen3.5 397B A17B
BenchmarkMistral Large 4Qwen3.5 397B A17BLeader
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 Large 4$0.0034Fits in one request
Qwen3.5 397B A17B$0.0016Fits in one request

Qwen3.5 397B A17B costs less

Repository review

50K input + 3K output tokens

Mistral Large 4$0.081Fits in one request
Qwen3.5 397B A17B$0.027Fits in one request

Qwen3.5 397B A17B costs less

Agent loop

200K input + 10K output tokens

Mistral Large 4$0.314Fits in one request
Qwen3.5 397B A17B$0.101Fits in one request

Qwen3.5 397B A17B 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 Large 4 and Qwen3.5 397B A17B
SpecificationMistral Large 4Qwen3.5 397B A17B
MakerMistral AIQwen
WeightsNo public weights listedOpen weights
ReleasedOctober 6, 2026February 16, 2026
Context window1.05M262K
Input $/Mtok$1.36$0.39
Output $/Mtok$4.18$2.34
Coding index56.4Not benchmarked
Independent measurements behind it51
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Mistral Large 4 better than Qwen3.5 397B A17B for coding?

Only Mistral Large 4 has a coding score, 56.4 on the Vibe Coding Index; Qwen3.5 397B A17B has none, so the two cannot be ranked on coding. Pick Qwen3.5 397B A17B for output tokens 1.8x cheaper ($2.34 vs $4.18 per million) and work measured by Mystery game puzzles or LMArena Text: hard prompts, where it leads.

Which is cheaper, Mistral Large 4 or Qwen3.5 397B A17B?

Mistral Large 4 costs $1.36 per million input tokens and $4.18 per million output tokens; Qwen3.5 397B A17B costs $0.39 and $2.34. Cost per solved task is known for neither of them.

Which has the bigger context window, Mistral Large 4 or Qwen3.5 397B A17B?

Mistral Large 4, with 1.05M tokens against 262K.

How many benchmarks is the Mistral Large 4 vs Qwen3.5 397B A17B comparison based on?

51 benchmarks have a result for both models as of October 22, 2026. Mistral Large 4's coding index rests on 5 independent benchmarks and Qwen3.5 397B A17B's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next