DeepSeekLLM matchup

DeepSeek-V4-Flashvs.DeepSeek-V4.1-Flash

What has improved?

DeepSeek-V4-Flash does not have enough benchmark results yet. DeepSeek-V4-Flash is cheaper: DeepSeek-V4.1-Flash costs 1.1 times (input) and 2.1 times (output) as much.

IntelligenceOverall index, 100 points = average

n/a

DeepSeek-V4-Flash

not ranked yet

99.7

DeepSeek-V4.1-Flash

Rank 29

DeepSeek-V4.1-Flash faster

SpeedTokens per second

123

DeepSeek-V4-Flash

176

DeepSeek-V4.1-Flash

DeepSeek-V4-Flash cheaper

Price$ per 1M tokens

$0.18

DeepSeek-V4-Flash

$0.26

DeepSeek-V4.1-Flash

DeepSeek-V4-Flash more popular

Popularity0 to 100

DeepSeek-V4-Flash

Rank 23 of 876

DeepSeek-V4.1-Flash

Rank 312 of 876

Choose DeepSeek-V4-Flash for

No clear advantage

Choose DeepSeek-V4.1-Flash for

Agents

Where is the difference?

DeepSeek-V4.1-Flash is ahead in 1 of 8 areas, DeepSeek-V4-Flash in none.

too little data: 7DeepSeek-V4.1-Flash ahead: 1

Areas in the overall index

AgentsDeepSeek-V4.1-Flash +2383.2 to 106.4

Codingonly DeepSeek-V4.1-Flash has a score

Mathematicsonly DeepSeek-V4.1-Flash has a score

Generalonly DeepSeek-V4.1-Flash has a score

Multimodalonly DeepSeek-V4.1-Flash has a score

Specialist fields

Financeonly DeepSeek-V4.1-Flash has a score

Legalonly DeepSeek-V4.1-Flash has a score

Healthonly 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.

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

Cybersecurityonly DeepSeek-V4.1-Flash has a score

Productivityonly DeepSeek-V4.1-Flash has a score

Educationonly 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 codeopenCoding without a score for DeepSeek-V4-Flash

Maths and data analysisopenMathematics without a score for DeepSeek-V4-Flash

Agents and workflowsDeepSeek-V4.1-FlashAgents 83.2 to 106.4

Fast chat repliesDeepSeek-V4.1-Flash123 to 176 tokens per second

Security analysisopenCybersecurity without a score for DeepSeek-V4-Flash

Many requests on a small budgetDeepSeek-V4-Flash$0.18 to $0.26 per 1M tokens

Finance, legal and medical textsopenFinance without a score for DeepSeek-V4-Flash, Legal without a score for DeepSeek-V4-Flash, Health without a score for DeepSeek-V4-Flash

Images, screenshots and PDFsopenMultimodal without a score for DeepSeek-V4-Flash

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-Flash

DeepSeek-V4.1-Flash

Earlier tests

Pelican on a bicycle

Prompt

Generate an SVG of a pelican riding a bicycle

Task origin: Simon Willison

DeepSeek-V4-Flash

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

Oct 5, 2026 · 98 s · $0.0011

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-flash-0731
Reasoning setting: high
Token limit including reasoning: 8,192 tokens
Output tokens: 8,192 tokens
Cost of the attempt: $0.0011
Response time: 97.8 s
API model reported in response: deepseek/deepseek-v4-flash-0731
Pinned endpoint: StreamLake | deepseek/deepseek-v4-flash-20260731
Temperature: Provider default
Test protocol: community-visual-tests-v1
Technical checks: Failed

Earlier attempts (3)

Oct 2, 2026API request failedReasoning setting: high
Oct 1, 2026API request failedReasoning setting: high
Sep 7, 2026API request failedReasoning setting: high

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

Popularity compared

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

DeepSeek-V4-Flash is more popular than DeepSeek-V4.1-Flash: 65 to 38 out of 100.

Over time

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

DeepSeek-V4-FlashDeepSeek-V4.1-Flash

All data side by side

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

Metric	DeepSeek-V4-Flash	DeepSeek-V4.1-Flash
Intelligence
Overall indexpoints, 100 = reference group average, higher is better	n/a	99.7
Rank	not ranked yet	Rank 29 of 92
Price per 1M tokens
Inputwhat you send	$0.14	$0.15
Outputwhat the model writes	$0.28	$0.60
Cost per task (own tests)average of 2 original-protocol tasks both models passed (SVG short test not included)	$0.002	$0.008
Speed
Tokens per second	123	176
Popularity
Popularitysearch, usage and mentions, 0 to 100	65Rank 23 of 876	38Rank 312 of 876
Technical
Context windowhow much text the model reads at once	1 M tokens≈ 1,500 A4 pages	1 M tokens≈ 1,500 A4 pages
Knowledge cutoff	n/a	n/a
Released	Apr 24, 2026	Sep 10, 2026
Availability	Limited access	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

DeepSeek-V4-Flash vs. DeepSeek V4.1 Flash 1017

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-FlashB: DeepSeek-V4.1-Flash

GDPval-AAOverall · higher is better1,440.6 elo1,600.0 eloArtificial AnalysisAs of 11/06/2026

LMArena Code Arena WebDevOverall · higher is betterTest setup not documented as identical1,5821,619LMArenaAs of 10/28/2026

LMArena Text, Style ControlOverall · higher is betterTest setup not documented as identical1,4391,476LMArenaAs of 10/28/2026

LMArena Code Arena WebDevHTML development · higher is betterTest setup not documented as identical1,5581,613LMArenaAs of 10/28/2026

LMArena Text, Style ControlBusiness, management and finance · higher is betterTest setup not documented as identical1,4351,478LMArenaAs of 10/28/2026

LMArena Code Arena WebDevReact development · higher is betterTest setup not documented as identical1,5851,629LMArenaAs of 10/28/2026

LMArena Text, Style ControlChinese · higher is betterTest setup not documented as identical1,4801,523LMArenaAs of 10/28/2026

LMArena Code Arena WebDevWeb development · higher is betterTest setup not documented as identical1,5821,619LMArenaAs of 10/28/2026

LMArena Text, Style ControlCoding · higher is betterTest setup not documented as identical1,4801,523LMArenaAs of 10/28/2026

LMArena Text, Style ControlCreative writing · higher is betterTest setup not documented as identical1,4101,441LMArenaAs of 10/28/2026

Show 24 more benchmarks

LMArena Text, Style ControlEnglish · higher is betterTest setup not documented as identical1,4501,488LMArenaAs of 10/28/2026

LMArena Text, Style ControlEntertainment, sports and media · higher is betterTest setup not documented as identical1,4071,450LMArenaAs of 10/28/2026

LMArena Text, Style ControlExcluding ties · higher is betterTest setup not documented as identical1,4361,486LMArenaAs of 10/28/2026

LMArena Text, Style ControlExpert prompts · higher is betterTest setup not documented as identical1,4671,516LMArenaAs of 10/28/2026

LMArena Text, Style ControlFrench prompts · higher is betterTest setup not documented as identical1,4581,482LMArenaAs of 10/28/2026

LMArena Text, Style ControlGerman prompts · higher is betterTest setup not documented as identical1,4341,489LMArenaAs of 10/28/2026

LMArena Text, Style ControlHard prompts · higher is betterTest setup not documented as identical1,4581,499LMArenaAs of 10/28/2026

LMArena Text, Style ControlHard prompts, English · higher is betterTest setup not documented as identical1,4651,504LMArenaAs of 10/28/2026

LMArena Text, Style ControlInstruction following · higher is betterTest setup not documented as identical1,4341,477LMArenaAs of 10/28/2026

LMArena Text, Style ControlJapanese prompts · higher is betterTest setup not documented as identical1,4251,452LMArenaAs of 10/28/2026

LMArena Text, Style ControlKorean prompts · higher is betterTest setup not documented as identical1,3791,444LMArenaAs of 10/28/2026

LMArena Text, Style ControlLegal and government · higher is betterTest setup not documented as identical1,4581,459LMArenaAs of 10/28/2026

LMArena Text, Style ControlLife, physical and social science · higher is betterTest setup not documented as identical1,4591,490LMArenaAs of 10/28/2026

LMArena Text, Style ControlLonger queries · higher is betterTest setup not documented as identical1,4481,481LMArenaAs of 10/28/2026

LMArena Text, Style ControlMath · higher is betterTest setup not documented as identical1,4421,498LMArenaAs of 10/28/2026

LMArena Text, Style ControlMathematical professions · higher is betterTest setup not documented as identical1,4451,495LMArenaAs of 10/28/2026

LMArena Text, Style ControlMedicine and healthcare · higher is betterTest setup not documented as identical1,4601,508LMArenaAs of 10/28/2026

LMArena Text, Style ControlMulti-turn · higher is betterTest setup not documented as identical1,4471,468LMArenaAs of 10/28/2026

LMArena Text, Style ControlNon-English · higher is betterTest setup not documented as identical1,4231,461LMArenaAs of 10/28/2026

LMArena Text, Style ControlPolish prompts · higher is betterTest setup not documented as identical1,4351,473LMArenaAs of 10/28/2026

LMArena Text, Style ControlRussian prompts · higher is betterTest setup not documented as identical1,4361,480LMArenaAs of 10/28/2026

LMArena Text, Style ControlSoftware and IT services · higher is betterTest setup not documented as identical1,4731,514LMArenaAs of 10/28/2026

LMArena Text, Style ControlSpanish prompts · higher is betterTest setup not documented as identical1,4301,463LMArenaAs of 10/28/2026

LMArena Text, Style ControlWriting, literature and language · higher is betterTest setup not documented as identical1,4221,456LMArenaAs of 10/28/2026

More comparisons

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

Compare another matchup

First modelSecond model

Predecessor and successor

SuccessorDeepSeek-V4.1-Flash vs. DeepSeek V4.1 Flash 1017Successor of DeepSeek-V4.1-Flash

The most popular comparisons

Show all 71 comparisons