Enter opens the highlighted result. Esc closes.

DeepSeek V4 Flash 0423 vs Step 3.5 Flash

DeepSeek V4 Flash 0423 leads Step 3.5 Flash on the Artificial Analysis Intelligence Index, 24.4 to 17.0, at about the same output price ($0.28 vs $0.30 per million). Updated October 21, 2026; 29 benchmarks have a result for both.

Replace DeepSeek V4 Flash 0423 Replace Step 3.5 Flash
DeepSeek V4 Flash 0423DeepSeek
Coding
No data
Overall
No data
Output $/M
$0.28
29
Step 3.5 FlashStepFun
Coding
No data
Overall
No data
Output $/M
$0.30
0
vs boards won of 29 shared

DeepSeek V4 Flash 0423 or Step 3.5 Flash: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick DeepSeek V4 Flash 0423 for output tokens 1.1x cheaper ($0.28 vs $0.30 per million) and a larger context window (1.05M against 262K tokens).

Model ADeepSeek V4 Flash 0423DeepSeekNot benchmarked1 independent benchmarkNo cost per solved taskModel BStep 3.5 FlashStepFunNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
29
DeepSeek V4 Flash 0423 only
20
Step 3.5 Flash only
6
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
DeepSeek V4 Flash 0423 not benchmarked, Step 3.5 Flash not benchmarked.
Widest category
Intelligence, 7.4 points apart on average over 1 shared benchmark.
Widest single gap
LMArena Text: Polish: DeepSeek V4 Flash 0423 1436 against Step 3.5 Flash 1389, 7.7 points apart on a 0 to 100 scale.
Output price
DeepSeek V4 Flash 0423 $0.28 against Step 3.5 Flash $0.30 per million output tokens, 1.1x apart.
Context window
DeepSeek V4 Flash 0423 takes 1.05M tokens, Step 3.5 Flash 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
CategoryDeepSeek V4 Flash 0423BarsStep 3.5 FlashTies
Coding20
Intelligence10
Reasoning30
Math20
Knowledge40
General170
All shared boards290
CodingLike-for-likeSix of these boards feed the Vibe Coding Index20
Coding benchmarks for DeepSeek V4 Flash 0423 and Step 3.5 Flash
BenchmarkDeepSeek V4 Flash 0423Step 3.5 FlashLeader
LMArena WebDev1582Not measuredOnly DeepSeek V4 Flash 0423 measured
AA Coding Index52.0Not measuredOnly DeepSeek V4 Flash 0423 measured
Terminal-Bench Hard (Artificial Analysis run)Not measured32.6%Only Step 3.5 Flash measured
WeirdML45.6%Not measuredOnly DeepSeek V4 Flash 0423 measured
ALE-Bench678.2Not measuredOnly DeepSeek V4 Flash 0423 measured
LMArena Text: coding14571436DeepSeek V4 Flash 0423
LMArena Text: software and IT14531434DeepSeek V4 Flash 0423
LMArena WebDev: React1585Not measuredOnly DeepSeek V4 Flash 0423 measured
LMArena WebDev: HTML1558Not measuredOnly DeepSeek V4 Flash 0423 measured
Neither model has a result on the other 30 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for DeepSeek V4 Flash 0423 and Step 3.5 Flash
BenchmarkDeepSeek V4 Flash 0423Step 3.5 FlashLeader
AA Intelligence Index24.417.0DeepSeek V4 Flash 0423
Epoch Capabilities Index146.1Not measuredOnly DeepSeek V4 Flash 0423 measured
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Agentic work benchmarks for DeepSeek V4 Flash 0423 and Step 3.5 Flash
BenchmarkDeepSeek V4 Flash 0423Step 3.5 FlashLeader
AA Agentic Index26.3Not measuredOnly DeepSeek V4 Flash 0423 measured
τ²-Bench TelecomNot measured94.4%Only Step 3.5 Flash measured
Neither model has a result on the other 39 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index30
Reasoning benchmarks for DeepSeek V4 Flash 0423 and Step 3.5 Flash
BenchmarkDeepSeek V4 Flash 0423Step 3.5 FlashLeader
GPQA Diamond (Artificial Analysis run)Not measured83.1%Only Step 3.5 Flash measured
Humanity's Last Exam (Artificial Analysis run)Not measured24.5%Only Step 3.5 Flash measured
SimpleBench46.3%Not measuredOnly DeepSeek V4 Flash 0423 measured
LMArena Text: hard prompts14441411DeepSeek V4 Flash 0423
LMArena Text: expert14411421DeepSeek V4 Flash 0423
LMArena Text: hard prompts in English14491421DeepSeek V4 Flash 0423
Kagi LLM Benchmark52.2%Not measuredOnly DeepSeek V4 Flash 0423 measured
Neither model has a result on the other 15 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index20
Math benchmarks for DeepSeek V4 Flash 0423 and Step 3.5 Flash
BenchmarkDeepSeek V4 Flash 0423Step 3.5 FlashLeader
LMArena Text: math14261408DeepSeek V4 Flash 0423
LMArena Text: mathematical work14321421DeepSeek V4 Flash 0423
Neither model has a result on the other 11 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
Knowledge benchmarks for DeepSeek V4 Flash 0423 and Step 3.5 Flash
BenchmarkDeepSeek V4 Flash 0423Step 3.5 FlashLeader
LMArena Text: science14461415DeepSeek V4 Flash 0423
LMArena Text: medicine and healthcare14481408DeepSeek V4 Flash 0423
LMArena Text: legal and government14391408DeepSeek V4 Flash 0423
LMArena Text: business and finance14251394DeepSeek V4 Flash 0423
Neither model has a result on the other 14 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for DeepSeek V4 Flash 0423 and Step 3.5 Flash
BenchmarkDeepSeek V4 Flash 0423Step 3.5 FlashLeader
Design Arena: websites1208Not measuredOnly DeepSeek V4 Flash 0423 measured
Design Arena: UI components1165Not measuredOnly DeepSeek V4 Flash 0423 measured
Design Arena: game dev1197Not measuredOnly DeepSeek V4 Flash 0423 measured
Design Arena: data viz1127Not measuredOnly DeepSeek V4 Flash 0423 measured
Design Arena: 3D1189Not measuredOnly DeepSeek V4 Flash 0423 measured
Design Arena: all code categories1205Not measuredOnly DeepSeek V4 Flash 0423 measured
Design Arena: SVG1155Not measuredOnly DeepSeek V4 Flash 0423 measured
Design Arena: ASCII art1109Not measuredOnly DeepSeek V4 Flash 0423 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index170
General benchmarks for DeepSeek V4 Flash 0423 and Step 3.5 Flash
BenchmarkDeepSeek V4 Flash 0423Step 3.5 FlashLeader
IFBenchNot measured66.5%Only Step 3.5 Flash measured
Long context reasoning (AA-LCR)Not measured63.0%Only Step 3.5 Flash measured
DTBench86.4%Not measuredOnly DeepSeek V4 Flash 0423 measured
LMCA35.9%Not measuredOnly DeepSeek V4 Flash 0423 measured
LMArena Text14321403DeepSeek V4 Flash 0423
LMArena Text: instruction following14211385DeepSeek V4 Flash 0423
LMArena Text: creative writing14031357DeepSeek V4 Flash 0423
LMArena Text: English14411417DeepSeek V4 Flash 0423
LMArena Text: non-English14191385DeepSeek V4 Flash 0423
LMArena Text: Chinese14631446DeepSeek V4 Flash 0423
LMArena Text: German14191405DeepSeek V4 Flash 0423
LMArena Text: Japanese13891353DeepSeek V4 Flash 0423
LMArena Text: Korean13831351DeepSeek V4 Flash 0423
LMArena Text: French14391421DeepSeek V4 Flash 0423
LMArena Text: Spanish14361419DeepSeek V4 Flash 0423
LMArena Text: Russian14271385DeepSeek V4 Flash 0423
LMArena Text: Polish14361389DeepSeek V4 Flash 0423
LMArena Text: multi-turn14491404DeepSeek V4 Flash 0423
LMArena Text: longer queries14341402DeepSeek V4 Flash 0423
LMArena Text: writing and language14101372DeepSeek V4 Flash 0423
LMArena Text: entertainment and media14001360DeepSeek V4 Flash 0423
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 DeepSeek V4 Flash 0423 and Step 3.5 Flash
BenchmarkDeepSeek V4 Flash 0423Step 3.5 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

DeepSeek V4 Flash 0423$0.0003Fits in one request
Step 3.5 Flash$0.0003Fits in one request

Step 3.5 Flash costs less

Repository review

50K input + 3K output tokens

DeepSeek V4 Flash 0423$0.0073Fits in one request
Step 3.5 Flash$0.0059Fits in one request

Step 3.5 Flash costs less

Agent loop

200K input + 10K output tokens

DeepSeek V4 Flash 0423$0.029Fits in one request
Step 3.5 Flash$0.023Fits in one request

Step 3.5 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 DeepSeek V4 Flash 0423 and Step 3.5 Flash
SpecificationDeepSeek V4 Flash 0423StepFun Step 3.5 Flash
MakerDeepSeekStepFun
WeightsOpen weightsOpen weights
ReleasedApril 24, 2026January 29, 2026
Context window1.05M262K
Input $/Mtok$0.13$0.10
Output $/Mtok$0.28$0.30
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it10
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V4 Flash 0423 better than Step 3.5 Flash for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick DeepSeek V4 Flash 0423 for output tokens 1.1x cheaper ($0.28 vs $0.30 per million) and a larger context window (1.05M against 262K tokens).

Which is cheaper, DeepSeek V4 Flash 0423 or Step 3.5 Flash?

DeepSeek V4 Flash 0423 costs $0.13 per million input tokens and $0.28 per million output tokens; Step 3.5 Flash costs $0.10 and $0.30. Cost per solved task is known for neither of them.

Which has the bigger context window, DeepSeek V4 Flash 0423 or Step 3.5 Flash?

DeepSeek V4 Flash 0423, with 1.05M tokens against 262K.

How many benchmarks is the DeepSeek V4 Flash 0423 vs Step 3.5 Flash comparison based on?

29 benchmarks have a result for both models as of October 21, 2026. DeepSeek V4 Flash 0423's coding index rests on 1 independent benchmark and Step 3.5 Flash's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next