Enter opens the highlighted result. Esc closes.

Mistral Large vs Qwen3.5-Flash

Qwen3.5-Flash costs 23.1x less per output token than Mistral Large ($0.26 vs $6.00 per million). Updated October 22, 2026; 35 benchmarks have a result for both.

Replace Mistral Large Replace Qwen3.5-Flash
Mistral LargeMistral AI
Coding
No data
Overall
No data
Output $/M
$6.00
0
Qwen3.5-FlashQwen
Coding
41.1
Overall
50.1
Output $/M
$0.26
35
vs boards won of 35 shared

Mistral Large or Qwen3.5-Flash: which to pick

Only Qwen3.5-Flash has a coding score, 41.1 on the Vibe Coding Index; Mistral Large has none, so the two cannot be ranked on coding.

Compare them on price, context and the boards below.

Model AMistral LargeMistral AINot benchmarkedNo coding benchmarkNo cost per solved taskModel BQwen3.5-FlashQwen41.1/1002 independent benchmarks$0.40 per solved task
Shared results
35
Mistral Large only
9
Qwen3.5-Flash only
20
Like-for-like categories
6 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 not benchmarked, Qwen3.5-Flash 41.1 from 2 benchmarks.
Widest category
Math, 44.5 points apart on average over 3 shared benchmarks.
Widest single gap
AIME: Mistral Large 9.2% against Qwen3.5-Flash 92.5%, 83.3 points apart on a 0 to 100 scale.
Output price
Mistral Large $6.00 against Qwen3.5-Flash $0.26 per million output tokens, 23.1x apart.
Context window
Mistral Large takes 128K tokens, Qwen3.5-Flash 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 LargeBarsQwen3.5-FlashTies
Coding03
Intelligence01
Reasoning04
Math03
Knowledge06
General018
All shared boards035
CodingLike-for-likeSix of these boards feed the Vibe Coding Index03
Coding benchmarks for Mistral Large and Qwen3.5-Flash
BenchmarkMistral LargeQwen3.5-FlashLeader
LMArena WebDevNot measured1244Only Qwen3.5-Flash measured
LiveCodeBench (Vals AI)37.1%83.3%Qwen3.5-Flash
SWE-bench Verified (Vals AI)Not measured64.4%Only Qwen3.5-Flash measured
LiveCodeBench (Artificial Analysis run)17.8%Not measuredOnly Mistral Large measured
ALE-BenchNot measured265.9Only Qwen3.5-Flash measured
LMArena Text: coding12751412Qwen3.5-Flash
LMArena Text: software and IT12741416Qwen3.5-Flash
LMArena WebDev: ReactNot measured1229Only Qwen3.5-Flash measured
LMArena WebDev: HTMLNot measured1291Only Qwen3.5-Flash measured
Neither model has a result on the other 30 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Mistral Large and Qwen3.5-Flash
BenchmarkMistral LargeQwen3.5-FlashLeader
AA Intelligence Index5.8Not measuredOnly Mistral Large measured
Epoch Capabilities Index122.1143.5Qwen3.5-Flash
Agentic workNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Agentic work benchmarks for Mistral Large and Qwen3.5-Flash
BenchmarkMistral LargeQwen3.5-FlashLeader
Neither model has a result on 41 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index04
Reasoning benchmarks for Mistral Large and Qwen3.5-Flash
BenchmarkMistral LargeQwen3.5-FlashLeader
GPQA Diamond47.7%82.8%Qwen3.5-Flash
MMMU Pro (Vals AI)Not measured81.9%Only Qwen3.5-Flash measured
GPQA Diamond (Artificial Analysis run)35.1%Not measuredOnly Mistral Large measured
Humanity's Last Exam (Artificial Analysis run)3.5%Not measuredOnly Mistral Large measured
GPQA Diamond (Epoch AI run)Not measured82.3%Only Qwen3.5-Flash measured
Chess puzzlesNot measured14.0%Only Qwen3.5-Flash measured
Mystery game puzzlesNot measured20.0%Only Qwen3.5-Flash measured
LMArena Text: hard prompts12571403Qwen3.5-Flash
LMArena Text: expert12081407Qwen3.5-Flash
LMArena Text: hard prompts in English12681409Qwen3.5-Flash
Neither model has a result on the other 12 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for Mistral Large and Qwen3.5-Flash
BenchmarkMistral LargeQwen3.5-FlashLeader
AIME9.2%92.5%Qwen3.5-Flash
MATH 500 (Vals AI)74.4%Not measuredOnly Mistral Large measured
MGSM (Vals AI)87.2%Not measuredOnly Mistral Large measured
OTIS Mock AIMENot measured84.4%Only Qwen3.5-Flash measured
FrontierMath, tiers 1 to 3Not measured18.2%Only Qwen3.5-Flash measured
LMArena Text: math12611407Qwen3.5-Flash
LMArena Text: mathematical work12571413Qwen3.5-Flash
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index06
Knowledge benchmarks for Mistral Large and Qwen3.5-Flash
BenchmarkMistral LargeQwen3.5-FlashLeader
MMLU Pro69.7%84.1%Qwen3.5-Flash
LegalBench (Vals AI)Not measured84.3%Only Qwen3.5-Flash measured
CaseLaw (Vals AI)Not measured56.0%Only Qwen3.5-Flash measured
CorpFin (Vals AI)Not measured63.6%Only Qwen3.5-Flash measured
TaxEval (Vals AI)63.8%72.2%Qwen3.5-Flash
MortgageTax (Vals AI)Not measured67.4%Only Qwen3.5-Flash measured
MedQA (Vals AI)76.2%Not measuredOnly Mistral Large measured
MedCode (Vals AI)Not measured33.0%Only Qwen3.5-Flash measured
MMLU Pro (Artificial Analysis run)51.5%Not measuredOnly Mistral Large measured
SimpleQA VerifiedNot measured20.3%Only Qwen3.5-Flash measured
MMLU68.8%Not measuredOnly Mistral Large measured
LMArena Text: science12601415Qwen3.5-Flash
LMArena Text: medicine and healthcare12551407Qwen3.5-Flash
LMArena Text: legal and government12751398Qwen3.5-Flash
LMArena Text: business and finance12381394Qwen3.5-Flash
Neither model has a result on the other 3 boards here
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Web design benchmarks for Mistral Large and Qwen3.5-Flash
BenchmarkMistral LargeQwen3.5-FlashLeader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index018
General benchmarks for Mistral Large and Qwen3.5-Flash
BenchmarkMistral LargeQwen3.5-FlashLeader
SAGE (Vals AI)Not measured42.5%Only Qwen3.5-Flash measured
MedScribe (Vals AI)Not measured70.6%Only Qwen3.5-Flash measured
DTBench60.8%82.9%Qwen3.5-Flash
LMCANot measured29.1%Only Qwen3.5-Flash measured
LMArena Text12651397Qwen3.5-Flash
LMArena Text: instruction following12491374Qwen3.5-Flash
LMArena Text: creative writing12421343Qwen3.5-Flash
LMArena Text: English12841404Qwen3.5-Flash
LMArena Text: non-English12351385Qwen3.5-Flash
LMArena Text: Chinese12391445Qwen3.5-Flash
LMArena Text: German12421390Qwen3.5-Flash
LMArena Text: Japanese11701369Qwen3.5-Flash
LMArena Text: Korean12021344Qwen3.5-Flash
LMArena Text: French13251413Qwen3.5-Flash
LMArena Text: Spanish12681400Qwen3.5-Flash
LMArena Text: Russian12521380Qwen3.5-Flash
LMArena Text: Polish11571376Qwen3.5-Flash
LMArena Text: multi-turn12601393Qwen3.5-Flash
LMArena Text: longer queries12611392Qwen3.5-Flash
LMArena Text: writing and language12611369Qwen3.5-Flash
LMArena Text: entertainment and media12301347Qwen3.5-Flash
Neither model has a result on the other 25 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Mistral Large and Qwen3.5-Flash
BenchmarkMistral LargeQwen3.5-FlashLeader
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$0.0050Fits in one request
Qwen3.5-Flash$0.0002Fits in one request

Qwen3.5-Flash costs less

Repository review

50K input + 3K output tokens

Mistral Large$0.118Fits in one request
Qwen3.5-Flash$0.0040Fits in one request

Qwen3.5-Flash costs less

Agent loop

200K input + 10K output tokens

Mistral Large$0.460Exceeds the context window
Qwen3.5-Flash$0.016Fits in one request

Qwen3.5-Flash 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 and Qwen3.5-Flash
SpecificationMistral LargeQwen3.5-Flash
MakerMistral AIQwen
WeightsNo public weights listedNo public weights listed
ReleasedFebruary 26, 2024February 25, 2026
Context window128K1M
Input $/Mtok$2.00$0.065
Output $/Mtok$6.00$0.26
Coding indexNot benchmarked41.1
Independent measurements behind it02
Cost per solved taskNot computable$0.40
SourceOpenRouter listingOpenRouter listing

Questions

Is Mistral Large better than Qwen3.5-Flash for coding?

Only Qwen3.5-Flash has a coding score, 41.1 on the Vibe Coding Index; Mistral Large has none, so the two cannot be ranked on coding. Compare them on price, context and the boards below.

Which is cheaper, Mistral Large or Qwen3.5-Flash?

Mistral Large costs $2.00 per million input tokens and $6.00 per million output tokens; Qwen3.5-Flash costs $0.065 and $0.26. Cost per solved task is known for Qwen3.5-Flash only.

Which has the bigger context window, Mistral Large or Qwen3.5-Flash?

Qwen3.5-Flash, with 1M tokens against 128K.

How many benchmarks is the Mistral Large vs Qwen3.5-Flash comparison based on?

35 benchmarks have a result for both models as of October 22, 2026. Mistral Large's coding index rests on 0 independent benchmarks and Qwen3.5-Flash's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next