DeepSeekMistral AILLM matchup

DeepSeek-V4.1-Flashvs.Mistral Medium 3.5

Which one is better?

DeepSeek-V4.1-Flash performs better than Mistral Medium 3.5 and is cheaper: Mistral Medium 3.5 costs 10 times (input) and 12.5 times (output) as much.

DeepSeek-V4.1-Flash ahead

IntelligenceOverall index, 100 points = average

99.7

DeepSeek-V4.1-Flash

Rank 29

46.8

Mistral Medium 3.5

Rank 88

DeepSeek-V4.1-Flash faster

SpeedTokens per second

176

DeepSeek-V4.1-Flash

144

Mistral Medium 3.5

DeepSeek-V4.1-Flash cheaper

Price$ per 1M tokens

$0.26

DeepSeek-V4.1-Flash

Mistral Medium 3.5

about as popular

Popularity0 to 100

DeepSeek-V4.1-Flash

Rank 312 of 876

Mistral Medium 3.5

Rank 317 of 876

Choose DeepSeek-V4.1-Flash for

FinanceAgentsEducationLegalCodingMultimodalHealthMathematicsGeneral

Choose Mistral Medium 3.5 for

No clear advantage

Where is the difference?

Strengths at a glance

DeepSeek-V4.1-FlashMistral Medium 3.5Median of all ranked models

CodingDeepSeek-V4.1-Flash ahead

DeepSeek-V4.1-Flash98.8Rank 30

Mistral Medium 3.551.2Rank 92

Median of ranked models84.1

95 % range: DeepSeek-V4.1-Flash 91.4 to 106.3, Mistral Medium 3.5 44.5 to 58.0.

AreaDeepSeek-V4.1-FlashMistral Medium 3.5

The same values and verdicts as the bars below. In the close-up the net starts at 30 points, just below the weaker model's lowest value; the reference group average is 100. Not in the net because a model has no own value there or the data are too thin: Reasoning, Knowledge.

DeepSeek-V4.1-Flash is ahead in 8 of 10 areas, Mistral Medium 3.5 in none.

DeepSeek-V4.1-Flash ahead: 8too little data: 2

Areas in the overall index

AgentsDeepSeek-V4.1-Flash +52106.4 to 54.0

CodingDeepSeek-V4.1-Flash +4898.8 to 51.2

MultimodalDeepSeek-V4.1-Flash +4695.7 to 49.7

MathematicsDeepSeek-V4.1-Flash +4097.3 to 57.0

GeneralDeepSeek-V4.1-Flash +4097.1 to 57.0

Reasoningonly Mistral Medium 3.5 has a score

Knowledgeonly Mistral Medium 3.5 has a score

Specialist fields

FinanceDeepSeek-V4.1-Flash +65103.7 to 38.7

LegalDeepSeek-V4.1-Flash +49100.8 to 51.9

HealthDeepSeek-V4.1-Flash +4595.5 to 50.1

Bar length shows the gap in index points (full width 15 points, one standard deviation of the reference group). Solid means clearly ahead, hatched not certain yet, a thin grey bar level.

Show 3 more areas that do not count toward the overall index

EducationDeepSeek-V4.1-Flash +5197.9 to 46.8

Cybersecurityonly DeepSeek-V4.1-Flash has a score

Productivityonly DeepSeek-V4.1-Flash has a score

Bar length shows the gap in index points (full width 15 points, one standard deviation of the reference group). Solid means clearly ahead, hatched not certain yet, a thin grey bar level.

Which model for which task?

Everyday tasks, translated from the area values above. Each row names the values it rests on.

TaskBetter choicebased on

Writing and debugging codeDeepSeek-V4.1-FlashCoding 98.8 to 51.2

Maths and data analysisDeepSeek-V4.1-FlashMathematics 97.3 to 57.0, Reasoning without a score for DeepSeek-V4.1-Flash

Facts and researchopenKnowledge without a score for DeepSeek-V4.1-Flash

Agents and workflowsDeepSeek-V4.1-FlashAgents 106.4 to 54.0

Fast chat repliesDeepSeek-V4.1-Flash176 to 144 tokens per second

Security analysisopenCybersecurity without a score for Mistral Medium 3.5

Many requests on a small budgetDeepSeek-V4.1-Flash$0.26 to $3 per 1M tokens

Finance, legal and medical textsDeepSeek-V4.1-FlashFinance 103.7 to 38.7, Legal 100.8 to 51.9, Health 95.5 to 50.1

Images, screenshots and PDFsDeepSeek-V4.1-FlashMultimodal 95.7 to 49.7

See for yourself: same task, one attempt

SVG short test

One SVG task with the same fixed settings for every model, without hidden thinking.

Prompt

Return only one standalone SVG of a pelican riding a bicycle. Use viewBox="0 0 800 600", simple shapes, two clearly visible wheels and a recognizable pelican with a long beak. At most 30 SVG elements and 1800 characters. No Markdown, explanations, comments, scripts, animation, CSS or external resources.

DeepSeek-V4.1-Flash

Mistral Medium 3.5

Earlier tests

Pelican on a bicycle

Prompt

Generate an SVG of a pelican riding a bicycle

Task origin: Simon Willison

DeepSeek-V4.1-Flash

The response reached the token limit. No complete recording is available.

Oct 5, 2026 · 26 s · $0.0049

Not yet visually reviewed. A successful recording does not confirm correct physics or full compliance with the prompt.

Test details

Run date: Oct 5, 2026
API provider: openrouter
Requested API model: deepseek/deepseek-v4.1-flash
Reasoning setting: high
Token limit including reasoning: 8,192 tokens
Output tokens: 8,191 tokens
Cost of the attempt: $0.0049
Response time: 25.8 s
API model reported in response: deepseek/deepseek-v4.1-flash
Pinned endpoint: DeepSeek | deepseek/deepseek-v4.1-flash-20260910
Temperature: Provider default
Test protocol: community-visual-tests-v1
Technical checks: Failed

Earlier attempts (2)

Oct 2, 2026API request failedReasoning setting: high
Oct 1, 2026API request failedReasoning setting: high

Mistral Medium 3.5

Oct 1, 2026 · 39 s · $0.06

Test details

Run date: Oct 1, 2026
API provider: openrouter
Requested API model: mistralai/mistral-medium-3-5
Reasoning setting: high
Token limit including reasoning: 8,192 tokens
Output tokens: 8,128 tokens
Cost of the attempt: $0.0610
Response time: 38.7 s
API model reported in response: mistralai/mistral-medium-3-5
Pinned endpoint: Mistral | mistralai/mistral-medium-3.5-20260430
Temperature: Provider default
Test protocol: community-visual-tests-v1
Technical checks: Passed, not a quality rating

Visually reviewed. This individual test does not establish overall model quality.

Earlier attempts (1)

Sep 7, 2026API request failedReasoning setting: high

DeepSeek-V4.1-Flash and Mistral Medium 3.5 in the overall index

Every model with a place in the overall index, both models of this matchup highlighted. You can add or hide other models.

Overall index (Gradually Meta-Score v4)

20 of 92 models

5 models in this view are measured at a lower reasoning effort than max in the overall index. Dashed column: lower reasoning effort than the top.

Claude Opus 5.5max126.1

Gemini 4 Carbonhigh125.8

Claude Fable 5.1max123.8

Claude Sonnet 5.5max122.8

Gemini 4 Argonhigh122.3

GPT-6 Astramax121.3

GPT-6.1 Solmax119.2

Muse Wonder Fullmax118.3

Claude Opus 5max117.2

Muse Wondermax113.4

Kimi K3.1 Promax112.9

Claude Fable 5max112.5

GPT-6 Solmax110.5

GPT-5.6 Solmax108.7

Muse Spark 1.3max107.4

Gemini 3.7 Flashhigh107.1

DeepSeek V4.1 Flash 1017max106.6

Gemini 3.8 Flashhigh106.5

DeepSeek-V4.1-Flashmax99.7

Mistral Medium 3.5high46.8

Claude Opus 5.5

Gemini 4 Carbon

Claude Fable 5.1

Claude Sonnet 5.5

Gemini 4 Argon

GPT-6 Astra

GPT-6.1 Sol

Muse Wonder Full

Claude Opus 5

Muse Wonder

Kimi K3.1 Pro

Claude Fable 5

GPT-6 Sol

GPT-5.6 Sol

Muse Spark 1.3

Gemini 3.7 Flash

DeepSeek V4.1 Flash 1017

Gemini 3.8 Flash

DeepSeek-V4.1-Flash

Mistral Medium 3.5

Popularity compared

How often the models are searched for, used and mentioned, on a scale from 0 to 100.

Both are about as popular: DeepSeek-V4.1-Flash 38, Mistral Medium 3.5 37 out of 100.

Over time

Weekly values from October 18, 2026 to November 6, 2026

DeepSeek-V4.1-FlashMistral Medium 3.5

All data side by side

The better value is bold. For the overall index only when the gap is clear.

Metric	DeepSeek-V4.1-Flash	Mistral Medium 3.5
Intelligence
Overall indexpoints, 100 = reference group average, higher is better	99.7	46.8
Rank	Rank 29 of 92	Rank 88 of 92
Price per 1M tokens
Inputwhat you send	$0.15	$1.50
Outputwhat the model writes	$0.60	$7.50
Cost per task (own tests)average of 2 original-protocol tasks both models passed (SVG short test not included)	$0.008	$0.10
Speed
Tokens per second	176	144
Popularity
Popularitysearch, usage and mentions, 0 to 100	38Rank 312 of 876	37Rank 317 of 876
Technical
Context windowhow much text the model reads at once	1 M tokens≈ 1,500 A4 pages	262,144 tokens≈ 390 A4 pages
Knowledge cutoff	n/a	n/a
Released	Sep 10, 2026	Apr 28, 2026
Availability	Active	Active
Open weights	yes	yes

DeepSeek-V4.1-Flash: At peak times (Mon, Tue, Wed, Thu, Fri, 01:00-04:00 UTC; Mon, Tue, Wed, Thu, Fri, 06:00-10:00 UTC) the price is $0.30 input and $1.20 output per 1M tokens. The table shows the off-peak price.

Prices without caching or batch discounts · Page count as a rule of thumb from Artificial Analysis

Is there a better choice?

Successor of DeepSeek-V4.1-FlashDeepSeek V4.1 Flash 1017

Overall index 106.6, rank 17$0.15 input and $0.60 output per 1M tokens

Mistral Medium 3.5 vs. DeepSeek V4.1 Flash 1017

Cheaper than DeepSeek-V4.1-FlashClaude Haiku 5.5

Overall index 103.4, rank 20$0.10 input and $0.50 output per 1M tokens

DeepSeek-V4.1-Flash vs. Claude Haiku 5.5

Best model in the overall indexClaude Opus 5.5

Overall index 126.1, rank 1$4 input and $20 output per 1M tokens

DeepSeek-V4.1-Flash vs. Claude Opus 5.5

Shared benchmarks

Single results from the same benchmark version, task and metric. A value is bold only with the same test setup and a clear gap.

A: DeepSeek-V4.1-FlashB: Mistral Medium 3.5

Code MigrationOverall · higher is betterTest setup not documented as identical45.6%5.1%Vals AIAs of 10/29/2026

EMBOverall · higher is betterTest setup not documented as identical57.2%11.2%Vals AIAs of 10/20/2026

Finance Agent (v2)Overall · higher is betterTest setup not documented as identical53.5%32.1%Vals AIAs of 10/29/2026

Legal Research BenchOverall · All-pass · higher is betterTest setup not documented as identical41.3%9.1%Vals AIAs of 11/05/2026

LMArena Code Arena WebDevOverall · higher is betterTest setup not documented as identical1,6191,264LMArenaAs of 10/28/2026

LMArena Text, Style ControlOverall · higher is betterTest setup not documented as identical1,4761,426LMArenaAs of 10/28/2026

LMArena Vision, Style ControlOverall · higher is betterTest setup not documented as identical1,2611,200LMArenaAs of 10/19/2026

MedCodeOverall · higher is betterTest setup not documented as identical41.2%33.8%Vals AIAs of 10/29/2026

MedScribeOverall · higher is betterTest setup not documented as identical85.5%67.7%Vals AIAs of 10/29/2026

ProofBench v1.1Overall · higher is betterTest setup not documented as identical54%9%Vals AIAs of 10/29/2026

Show 54 more benchmarks

SAGEOverall · higher is betterTest setup not documented as identical85.4%72.0%Vals AIAs of 11/05/2026

Tax Agent BenchOverall · higher is betterTest setup not documented as identical26.6%4.5%Vals AIAs of 11/05/2026

Vibe Code Bench v1.1Overall · higher is betterTest setup not documented as identical84.7%2.9%Vals AIAs of 11/05/2026

Code MigrationCLI · higher is betterTest setup not documented as identical37.5%5.0%Vals AIAs of 10/29/2026

EMBComps · higher is betterTest setup not documented as identical43.9%18.1%Vals AIAs of 10/20/2026

Finance Agent (v2)Adjustments · higher is betterTest setup not documented as identical49.2%27.3%Vals AIAs of 10/29/2026

Legal Research BenchAdministrative / Regulatory · All-pass · higher is betterTest setup not documented as identical53.0%7.6%Vals AIAs of 11/05/2026

LMArena Code Arena WebDevHTML development · higher is betterTest setup not documented as identical1,6131,308LMArenaAs of 10/28/2026

LMArena Text, Style ControlBusiness, management and finance · higher is betterTest setup not documented as identical1,4781,431LMArenaAs of 10/28/2026

LMArena Vision, Style ControlChinese · higher is betterTest setup not documented as identical1,3111,217LMArenaAs of 10/19/2026

SAGEComputer Science · higher is betterTest setup not documented as identical91.1%72.6%Vals AIAs of 11/05/2026

Tax Agent BenchControversy & Precedence Analysis · higher is betterTest setup not documented as identical3.3%3.3%Vals AIAs of 11/05/2026

Code MigrationCOBOL · higher is betterTest setup not documented as identical70.0%5.5%Vals AIAs of 10/29/2026

EMBDataroom · higher is betterTest setup not documented as identical73.9%13.4%Vals AIAs of 10/20/2026

Finance Agent (v2)All-Pass · higher is betterTest setup not documented as identical41.1%21.6%Vals AIAs of 10/29/2026

Legal Research BenchAdministrative / Regulatory · Weighted partial credit (weighted pass) · higher is betterTest setup not documented as identical89.1%67.5%Vals AIAs of 11/05/2026

LMArena Code Arena WebDevReact development · higher is betterTest setup not documented as identical1,6291,254LMArenaAs of 10/28/2026

LMArena Text, Style ControlChinese · higher is betterTest setup not documented as identical1,5231,448LMArenaAs of 10/28/2026

LMArena Vision, Style ControlCreative writing with images · higher is betterTest setup not documented as identical1,2541,195LMArenaAs of 10/19/2026

SAGELinear Algebra · higher is betterTest setup not documented as identical72.7%64.8%Vals AIAs of 11/05/2026

Tax Agent BenchControversy & Precedence Analysis (weighted pass) · higher is betterTest setup not documented as identical52.8%18.4%Vals AIAs of 11/05/2026

Code MigrationCode Quality · higher is betterTest setup not documented as identical4.411 / 52.987 / 5Vals AIAs of 10/29/2026

EMBDCF · higher is betterTest setup not documented as identical51.0%2.2%Vals AIAs of 10/20/2026

Finance Agent (v2)Comparables · higher is betterTest setup not documented as identical46.1%31.5%Vals AIAs of 10/29/2026

Legal Research BenchBusiness & Commercial · All-pass · higher is betterTest setup not documented as identical39.5%9.3%Vals AIAs of 11/05/2026

LMArena Code Arena WebDevWeb development · higher is betterTest setup not documented as identical1,6191,264LMArenaAs of 10/28/2026

LMArena Text, Style ControlCoding · higher is betterTest setup not documented as identical1,5231,477LMArenaAs of 10/28/2026

LMArena Vision, Style ControlDiagram understanding · higher is betterTest setup not documented as identical1,2931,242LMArenaAs of 10/19/2026

SAGEPartial Differential Equations · higher is betterTest setup not documented as identical90.3%81.2%Vals AIAs of 11/05/2026

Tax Agent BenchCurrent & Temporal Analysis · higher is betterTest setup not documented as identical39.0%6.5%Vals AIAs of 11/05/2026

EMBLBO · higher is betterTest setup not documented as identical54.2%9.6%Vals AIAs of 10/20/2026

Finance Agent (v2)Disclosure Analysis · higher is betterTest setup not documented as identical61.3%40.2%Vals AIAs of 10/29/2026

Legal Research BenchBusiness & Commercial · Weighted partial credit (weighted pass) · higher is betterTest setup not documented as identical86.7%71.3%Vals AIAs of 11/05/2026

LMArena Text, Style ControlCreative writing · higher is betterTest setup not documented as identical1,4411,400LMArenaAs of 10/28/2026

LMArena Vision, Style ControlEnglish · higher is betterTest setup not documented as identical1,2681,216LMArenaAs of 10/19/2026

Tax Agent BenchCurrent & Temporal Analysis (weighted pass) · higher is betterTest setup not documented as identical71.9%29.4%Vals AIAs of 11/05/2026

EMBM&A · higher is betterTest setup not documented as identical57.8%10.7%Vals AIAs of 10/20/2026

Finance Agent (v2)Earnings Analysis · higher is betterTest setup not documented as identical72.9%42.1%Vals AIAs of 10/29/2026

Legal Research BenchCivil Litigation · All-pass · higher is betterTest setup not documented as identical48.1%11.1%Vals AIAs of 11/05/2026

LMArena Text, Style ControlEnglish · higher is betterTest setup not documented as identical1,4881,444LMArenaAs of 10/28/2026

LMArena Vision, Style ControlHomework · higher is betterTest setup not documented as identical1,3071,217LMArenaAs of 10/19/2026

Tax Agent BenchFact-Pattern Analysis · higher is betterTest setup not documented as identical27.2%2.3%Vals AIAs of 11/05/2026

EMBMisc · higher is betterTest setup not documented as identical53.6%14.1%Vals AIAs of 10/20/2026

Finance Agent (v2)Financial Modeling · higher is betterTest setup not documented as identical23.1%5.1%Vals AIAs of 10/29/2026

Legal Research BenchCivil Litigation · Weighted partial credit (weighted pass) · higher is betterTest setup not documented as identical87.1%66.0%Vals AIAs of 11/05/2026

LMArena Text, Style ControlEntertainment, sports and media · higher is betterTest setup not documented as identical1,4501,396LMArenaAs of 10/28/2026

LMArena Vision, Style ControlHumor · higher is betterTest setup not documented as identical1,2431,196LMArenaAs of 10/19/2026

Tax Agent BenchFact-Pattern Analysis (weighted pass) · higher is betterTest setup not documented as identical60.6%24.4%Vals AIAs of 11/05/2026

EMBOperating · higher is betterTest setup not documented as identical66.0%10.2%Vals AIAs of 10/20/2026

Finance Agent (v2)General Qualitative Analysis · higher is betterTest setup not documented as identical67.4%47.9%Vals AIAs of 10/29/2026

Legal Research BenchConstitutional / Civil Rights · All-pass · higher is betterTest setup not documented as identical36.8%10.5%Vals AIAs of 11/05/2026

LMArena Text, Style ControlExcluding ties · higher is betterTest setup not documented as identical1,4861,420LMArenaAs of 10/28/2026

LMArena Vision, Style ControlOptical character recognition · higher is betterTest setup not documented as identical1,2721,215LMArenaAs of 10/19/2026

Tax Agent BenchForms & Filings · higher is betterTest setup not documented as identical12.3%0.0%Vals AIAs of 11/05/2026

More comparisons

Compare DeepSeek-V4.1-Flash and Mistral Medium 3.5 with the models people compare them with most often.

DeepSeek-V4.1-Flashvs.Mistral Medium 3.5

Choose DeepSeek-V4.1-Flash for

Choose Mistral Medium 3.5 for

Where is the difference?

Strengths at a glance

Which model for which task?

See for yourself: same task, one attempt

SVG short test

DeepSeek-V4.1-Flash

Mistral Medium 3.5

Pelican on a bicycle

DeepSeek-V4.1-Flash and Mistral Medium 3.5 in the overall index

Overall index (Gradually Meta-Score v4)

Popularity compared

Over time

All data side by side

Is there a better choice?

Shared benchmarks

More comparisons

Compare another matchup

Predecessor and successor

The most popular comparisons