Enter opens the highlighted result. Esc closes.

DeepSeek V4.1 Flash vs Mistral Large 4

DeepSeek V4.1 Flash leads Mistral Large 4 on coding, 62.5 to 56.4 on the Vibe Coding Index, and DeepSeek V4.1 Flash costs 5.0x less per output token ($0.84 vs $4.18 per million). Updated October 22, 2026; 80 benchmarks have a result for both.

Replace DeepSeek V4.1 Flash Replace Mistral Large 4
DeepSeek V4.1 FlashDeepSeek
Coding
62.5
Overall
62.4
Output $/M
$0.84
69
Mistral Large 4Mistral AI
Coding
56.4
Overall
54.6
Output $/M
$4.18
9
vs boards won of 80 shared, 2 tied

DeepSeek V4.1 Flash or Mistral Large 4: which to pick

Pick DeepSeek V4.1 Flash for coding: it scores 62.5 on the Vibe Coding Index against 56.4 for Mistral Large 4.

Pick Mistral Large 4 for work measured by Terminal-Bench 4 (Vals AI) or IOI (Vals AI), where it leads.

Model ADeepSeek V4.1 FlashDeepSeek62.5/1005 independent benchmarksNo cost per solved taskModel BMistral Large 4Mistral AI56.4/1005 independent benchmarksNo cost per solved task
Shared results
80
DeepSeek V4.1 Flash only
21
Mistral Large 4 only
1
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
DeepSeek V4.1 Flash 62.5 from 5 benchmarks, Mistral Large 4 56.4 from 5 benchmarks.
Widest category
Agentic work, 22.4 points apart on average over 8 shared benchmarks.
Widest single gap
LiveBench browser: DeepSeek V4.1 Flash 84.0% against Mistral Large 4 8.0%, 76.0 points apart on a 0 to 100 scale.
Output price
DeepSeek V4.1 Flash $0.84 against Mistral Large 4 $4.18 per million output tokens, 5.0x apart.
Context window
Both take 1.05M 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
CategoryDeepSeek V4.1 FlashBarsMistral Large 4Ties
Coding114
Intelligence11
Agentic work62
Reasoning100
Math402 ties
Knowledge60
Web design90
General222
All shared boards6992 ties
CodingLike-for-likeSix of these boards feed the Vibe Coding Index114
Coding benchmarks for DeepSeek V4.1 Flash and Mistral Large 4
BenchmarkDeepSeek V4.1 FlashMistral Large 4Leader
LiveBench coding90.2%60.0%DeepSeek V4.1 Flash
LMArena WebDev16181543DeepSeek V4.1 Flash
Terminal-Bench 4 (Vals AI)19.7%27.8%Mistral Large 4
Vibe Code Bench (Vals AI)84.7%78.4%DeepSeek V4.1 Flash
Code migration (Vals AI)45.6%30.6%DeepSeek V4.1 Flash
ProgramBench (Vals AI)0.5%Not measuredOnly DeepSeek V4.1 Flash measured
IOI (Vals AI)40.3%45.3%Mistral Large 4
Terminal-Bench 2.1 (Vals AI)74.5%Not measuredOnly DeepSeek V4.1 Flash measured
SWE-bench Multimodal (Vals AI)46.5%33.1%DeepSeek V4.1 Flash
Vibe Code Bench 1-100 (Vals AI)16.4%14.3%DeepSeek V4.1 Flash
SkillsBench (Vals AI)69.8%Not measuredOnly DeepSeek V4.1 Flash measured
CyberBench (Vals AI)73.7%Not measuredOnly DeepSeek V4.1 Flash measured
SciCode51.9%54.2%Mistral Large 4
FrontierCode43.9%39.4%DeepSeek V4.1 Flash
ALE-Bench1092.31213.2Mistral Large 4
LMArena Text: coding15021478DeepSeek V4.1 Flash
LMArena Text: software and IT14961467DeepSeek V4.1 Flash
LMArena WebDev: React16281559DeepSeek V4.1 Flash
LMArena WebDev: HTML16121487DeepSeek V4.1 Flash
LMArena WebDev: from an image1606Not measuredOnly DeepSeek V4.1 Flash measured
Neither model has a result on the other 19 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
Intelligence benchmarks for DeepSeek V4.1 Flash and Mistral Large 4
BenchmarkDeepSeek V4.1 FlashMistral Large 4Leader
AA Intelligence Index24.738.4Mistral Large 4
Epoch Capabilities Index155.9150.0DeepSeek V4.1 Flash
Agentic workLike-for-likePublic boards, shown as published, kept out of the index62
Agentic work benchmarks for DeepSeek V4.1 Flash and Mistral Large 4
BenchmarkDeepSeek V4.1 FlashMistral Large 4Leader
LiveBench research86.8%28.1%DeepSeek V4.1 Flash
LiveBench browser84.0%8.0%DeepSeek V4.1 Flash
LiveBench long agentic40.1%11.8%DeepSeek V4.1 Flash
SREBench (Vals AI)0.8%Not measuredOnly DeepSeek V4.1 Flash measured
Finance Agent (Vals AI)53.5%54.7%Mistral Large 4
Tax Agent Bench (Vals AI)26.6%30.4%Mistral Large 4
Legal Research Bench (Vals AI)41.4%31.7%DeepSeek V4.1 Flash
Harvey's Legal Agent Benchmark (Vals AI)Not measured17.5%Only Mistral Large 4 measured
Excel Modeling Benchmark (Vals AI)57.2%56.2%DeepSeek V4.1 Flash
BioMysteryBench (Vals AI)67.8%67.0%DeepSeek V4.1 Flash
Terminal-Bench-Science (Vals AI)0.0%Not measuredOnly DeepSeek V4.1 Flash measured
Vals Science Index29.6%Not measuredOnly DeepSeek V4.1 Flash measured
APEX-Agents39.5%Not measuredOnly DeepSeek V4.1 Flash measured
Neither model has a result on the other 28 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index100
Reasoning benchmarks for DeepSeek V4.1 Flash and Mistral Large 4
BenchmarkDeepSeek V4.1 FlashMistral Large 4Leader
LiveBench reasoning86.7%83.9%DeepSeek V4.1 Flash
MysteryMechanism (Vals AI)21.2%12.2%DeepSeek V4.1 Flash
Humanity's Last Exam (Artificial Analysis run)39.2%35.0%DeepSeek V4.1 Flash
GPQA Diamond (Epoch AI run)89.8%88.1%DeepSeek V4.1 Flash
ARC-AGI94.5%Not measuredOnly DeepSeek V4.1 Flash measured
ARC-AGI-272.9%Not measuredOnly DeepSeek V4.1 Flash measured
Chess puzzles48.0%33.0%DeepSeek V4.1 Flash
Mystery game puzzles43.0%17.0%DeepSeek V4.1 Flash
LMArena Text: hard prompts14831444DeepSeek V4.1 Flash
LMArena Text: expert15011444DeepSeek V4.1 Flash
LMArena Text: hard prompts in English14881442DeepSeek V4.1 Flash
LMArena Vision: diagrams12971288DeepSeek V4.1 Flash
LMArena Vision: homework1307Not measuredOnly DeepSeek V4.1 Flash measured
Neither model has a result on the other 9 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index40
Math benchmarks for DeepSeek V4.1 Flash and Mistral Large 4
BenchmarkDeepSeek V4.1 FlashMistral Large 4Leader
OTIS Mock AIME98.3%98.3%Tie
FrontierMath, tiers 1 to 367.4%58.6%DeepSeek V4.1 Flash
FrontierMath, tier 426.8%26.8%Tie
ProofBench54.0%10.0%DeepSeek V4.1 Flash
LMArena Text: math14781469DeepSeek V4.1 Flash
LMArena Text: mathematical work14851462DeepSeek V4.1 Flash
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index60
Knowledge benchmarks for DeepSeek V4.1 Flash and Mistral Large 4
BenchmarkDeepSeek V4.1 FlashMistral Large 4Leader
LegalBench (Vals AI)83.3%Not measuredOnly DeepSeek V4.1 Flash measured
MedCode (Vals AI)41.2%40.7%DeepSeek V4.1 Flash
SimpleQA Verified42.9%20.0%DeepSeek V4.1 Flash
LMArena Text: science14691448DeepSeek V4.1 Flash
LMArena Text: medicine and healthcare14841433DeepSeek V4.1 Flash
LMArena Text: legal and government14431425DeepSeek V4.1 Flash
LMArena Text: business and finance14611439DeepSeek V4.1 Flash
Neither model has a result on the other 11 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index90
Web design benchmarks for DeepSeek V4.1 Flash and Mistral Large 4
BenchmarkDeepSeek V4.1 FlashMistral Large 4Leader
Design Arena: websites13081257DeepSeek V4.1 Flash
Design Arena: UI components13121272DeepSeek V4.1 Flash
Design Arena: game dev13301225DeepSeek V4.1 Flash
Design Arena: data viz12911275DeepSeek V4.1 Flash
Design Arena: 3D13551252DeepSeek V4.1 Flash
Design Arena: all code categories13201259DeepSeek V4.1 Flash
Design Arena: SVG12451232DeepSeek V4.1 Flash
Design Arena: ASCII art12651202DeepSeek V4.1 Flash
LiveBench design79.2%65.6%DeepSeek V4.1 Flash
GeneralLike-for-likePublic boards, shown as published, kept out of the index222
General benchmarks for DeepSeek V4.1 Flash and Mistral Large 4
BenchmarkDeepSeek V4.1 FlashMistral Large 4Leader
LiveBench data analysis79.3%76.5%DeepSeek V4.1 Flash
Public Benefits Bench (Vals AI)64.3%Not measuredOnly DeepSeek V4.1 Flash measured
SAGE (Vals AI)47.9%Not measuredOnly DeepSeek V4.1 Flash measured
MedScribe (Vals AI)85.5%80.4%DeepSeek V4.1 Flash
Long context reasoning (AA-LCR)84.0%81.3%DeepSeek V4.1 Flash
DTBench89.9%88.2%DeepSeek V4.1 Flash
LMCA47.0%35.8%DeepSeek V4.1 Flash
Surface Evolver Bench46.3%28.1%DeepSeek V4.1 Flash
Furniture assembly34.2%20.8%DeepSeek V4.1 Flash
LMArena Text14641431DeepSeek V4.1 Flash
LMArena Text: instruction following14731422DeepSeek V4.1 Flash
LMArena Text: creative writing14371363DeepSeek V4.1 Flash
LMArena Vision12781272DeepSeek V4.1 Flash
LMArena Text: English14731433DeepSeek V4.1 Flash
LMArena Text: non-English14491422DeepSeek V4.1 Flash
LMArena Text: Chinese15011492DeepSeek V4.1 Flash
LMArena Text: German1470Not measuredOnly DeepSeek V4.1 Flash measured
LMArena Text: Japanese14321415DeepSeek V4.1 Flash
LMArena Text: Korean1436Not measuredOnly DeepSeek V4.1 Flash measured
LMArena Text: French14651492Mistral Large 4
LMArena Text: Spanish14591455DeepSeek V4.1 Flash
LMArena Text: Russian14671417DeepSeek V4.1 Flash
LMArena Text: Polish1457Not measuredOnly DeepSeek V4.1 Flash measured
LMArena Text: multi-turn14611435DeepSeek V4.1 Flash
LMArena Text: longer queries14731428DeepSeek V4.1 Flash
LMArena Text: writing and language14501386DeepSeek V4.1 Flash
LMArena Text: entertainment and media14451378DeepSeek V4.1 Flash
LMArena Vision: English12881283DeepSeek V4.1 Flash
LMArena Vision: Chinese1327Not measuredOnly DeepSeek V4.1 Flash measured
LMArena Vision: reading text12821284Mistral Large 4
LMArena Vision: humor1260Not measuredOnly DeepSeek V4.1 Flash measured
LMArena Vision: creative writing1275Not measuredOnly DeepSeek V4.1 Flash 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 DeepSeek V4.1 Flash and Mistral Large 4
BenchmarkDeepSeek V4.1 FlashMistral Large 4Leader
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

DeepSeek V4.1 Flash$0.0006Fits in one request
Mistral Large 4$0.0034Fits in one request

DeepSeek V4.1 Flash costs less

Repository review

50K input + 3K output tokens

DeepSeek V4.1 Flash$0.014Fits in one request
Mistral Large 4$0.081Fits in one request

DeepSeek V4.1 Flash costs less

Agent loop

200K input + 10K output tokens

DeepSeek V4.1 Flash$0.053Fits in one request
Mistral Large 4$0.314Fits in one request

DeepSeek V4.1 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 DeepSeek V4.1 Flash and Mistral Large 4
SpecificationDeepSeek V4.1 FlashMistral Large 4
MakerDeepSeekMistral AI
WeightsOpen weightsNo public weights listed
ReleasedSeptember 10, 2026October 6, 2026
Context window1.05M1.05M
Input $/Mtok$0.2225$1.36
Output $/Mtok$0.84$4.18
Coding index62.556.4
Independent measurements behind it55
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V4.1 Flash better than Mistral Large 4 for coding?

Pick DeepSeek V4.1 Flash for coding: it scores 62.5 on the Vibe Coding Index against 56.4 for Mistral Large 4. Pick Mistral Large 4 for work measured by Terminal-Bench 4 (Vals AI) or IOI (Vals AI), where it leads.

Which is cheaper, DeepSeek V4.1 Flash or Mistral Large 4?

DeepSeek V4.1 Flash costs $0.2225 per million input tokens and $0.84 per million output tokens; Mistral Large 4 costs $1.36 and $4.18. Cost per solved task is known for neither of them.

Which has the bigger context window, DeepSeek V4.1 Flash or Mistral Large 4?

Neither: both take 1.05M tokens.

How many benchmarks is the DeepSeek V4.1 Flash vs Mistral Large 4 comparison based on?

80 benchmarks have a result for both models as of October 22, 2026. DeepSeek V4.1 Flash's coding index rests on 5 independent benchmarks and Mistral Large 4's on 5. 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/deepseek-v4-1-flash-vs-mistral-large-4-0" title="DeepSeek V4.1 Flash vs Mistral Large 4, 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/deepseek-v4-1-flash-vs-mistral-large-4-0">LLMBenchmark.ai, DeepSeek V4.1 Flash vs Mistral Large 4</a></p>