Enter opens the highlighted result. Esc closes.

DeepSeek V4 Flash 0423 vs DeepSeek V4 Pro 0423

Updated October 21, 2026. 47 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace DeepSeek V4 Flash 0423 Replace DeepSeek V4 Pro 0423
DeepSeek V4 Flash 0423DeepSeek
Coding
54.6
Overall
24.4
Output $/M
$0.182
4
DeepSeek V4 Pro 0423DeepSeek
Coding
35.3
Overall
30.4
Output $/M
$1.9105
42
vs boards won of 47 shared, 1 tied

Decision reading

Pick DeepSeek V4 Flash 0423 for coding: it scores 54.6 on the Vibe Coding Index against 35.3 for DeepSeek V4 Pro 0423.

Pick DeepSeek V4 Pro 0423 when what matters is AA Coding Index or WeirdML, where it leads.

Model ADeepSeek V4 Flash 0423DeepSeek54.6/1001 independent benchmarkNo cost per solved taskModel BDeepSeek V4 Pro 0423DeepSeek35.3/1001 independent benchmark$0.57 per solved task
Shared results
47
DeepSeek V4 Flash 0423 only
1
DeepSeek V4 Pro 0423 only
36
Like-for-like categories
8 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

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 54.6 from 1 benchmark, DeepSeek V4 Pro 0423 35.3 from 1 benchmark.
Widest category
Coding, 11.3 points apart on average over 8 shared benchmarks.
Widest single gap
LMArena WebDev: React: DeepSeek V4 Flash 0423 1585 against DeepSeek V4 Pro 0423 1441, 24.0 points apart on a 0 to 100 scale.
Output price
DeepSeek V4 Flash 0423 $0.182 against DeepSeek V4 Pro 0423 $1.9105 per million output tokens, 10.5x 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 Flash 0423BarsDeepSeek V4 Pro 0423Ties
Coding35
Intelligence02
Agentic work001 tie
Reasoning03
Math02
Knowledge04
Web design17
General019
All shared boards4421 tie
CodingLike-for-likeFour of these boards feed the Vibe Coding Index35
Coding benchmarks for DeepSeek V4 Flash 0423 and DeepSeek V4 Pro 0423
BenchmarkDeepSeek V4 Flash 0423DeepSeek V4 Pro 0423Leader
LMArena WebDev15821447DeepSeek V4 Flash 0423
AA Coding Index52.059.4DeepSeek V4 Pro 0423
LiveCodeBench (Vals AI)Not measured87.5%Only DeepSeek V4 Pro 0423 measured
SWE-bench Verified (Vals AI)Not measured77.4%Only DeepSeek V4 Pro 0423 measured
Terminal-Bench 4 (Vals AI)Not measured11.1%Only DeepSeek V4 Pro 0423 measured
Vibe Code Bench (Vals AI)Not measured49.9%Only DeepSeek V4 Pro 0423 measured
Code migration (Vals AI)Not measured26.2%Only DeepSeek V4 Pro 0423 measured
ProgramBench (Vals AI)Not measured0.0%Only DeepSeek V4 Pro 0423 measured
Terminal-Bench 2.1 (Vals AI)Not measured50.2%Only DeepSeek V4 Pro 0423 measured
SkillsBench (Vals AI)Not measured51.3%Only DeepSeek V4 Pro 0423 measured
FrontierCodeNot measured17.6%Only DeepSeek V4 Pro 0423 measured
WeirdML45.6%48.9%DeepSeek V4 Pro 0423
ALE-Bench678.21006.1DeepSeek V4 Pro 0423
LMArena Text: coding14571470DeepSeek V4 Pro 0423
LMArena Text: software and IT14531469DeepSeek V4 Pro 0423
LMArena WebDev: React15851441DeepSeek V4 Flash 0423
LMArena WebDev: HTML15581435DeepSeek V4 Flash 0423
Neither model has a result on the other 21 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for DeepSeek V4 Flash 0423 and DeepSeek V4 Pro 0423
BenchmarkDeepSeek V4 Flash 0423DeepSeek V4 Pro 0423Leader
AA Intelligence Index24.430.4DeepSeek V4 Pro 0423
Epoch Capabilities Index146.1149.1DeepSeek V4 Pro 0423
Agentic workLike-for-likePublic boards, shown as published, kept out of the index00
Agentic work benchmarks for DeepSeek V4 Flash 0423 and DeepSeek V4 Pro 0423
BenchmarkDeepSeek V4 Flash 0423DeepSeek V4 Pro 0423Leader
AA Agentic Index26.326.3Tie
Design Arena: agents building web appsNot measured1000Only DeepSeek V4 Pro 0423 measured
Design Arena: agents building full-stack appsNot measured948Only DeepSeek V4 Pro 0423 measured
Design Arena: agents building Godot gamesNot measured1059Only DeepSeek V4 Pro 0423 measured
Finance Agent (Vals AI)Not measured44.1%Only DeepSeek V4 Pro 0423 measured
Tax Agent Bench (Vals AI)Not measured25.2%Only DeepSeek V4 Pro 0423 measured
Legal Research Bench (Vals AI)Not measured23.1%Only DeepSeek V4 Pro 0423 measured
Excel Modeling Benchmark (Vals AI)Not measured51.6%Only DeepSeek V4 Pro 0423 measured
Vending-Bench 2Not measured$3,285Only DeepSeek V4 Pro 0423 measured
Neither model has a result on the other 30 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index03
Reasoning benchmarks for DeepSeek V4 Flash 0423 and DeepSeek V4 Pro 0423
BenchmarkDeepSeek V4 Flash 0423DeepSeek V4 Pro 0423Leader
GPQA DiamondNot measured89.4%Only DeepSeek V4 Pro 0423 measured
GPQA Diamond (Epoch AI run)Not measured90.9%Only DeepSeek V4 Pro 0423 measured
SimpleBench46.3%Not measuredOnly DeepSeek V4 Flash 0423 measured
Chess puzzlesNot measured19.0%Only DeepSeek V4 Pro 0423 measured
Mystery game puzzlesNot measured17.0%Only DeepSeek V4 Pro 0423 measured
LMArena Text: hard prompts14441461DeepSeek V4 Pro 0423
LMArena Text: expert14411463DeepSeek V4 Pro 0423
LMArena Text: hard prompts in English14491466DeepSeek V4 Pro 0423
Neither model has a result on the other 13 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for DeepSeek V4 Flash 0423 and DeepSeek V4 Pro 0423
BenchmarkDeepSeek V4 Flash 0423DeepSeek V4 Pro 0423Leader
OTIS Mock AIMENot measured96.7%Only DeepSeek V4 Pro 0423 measured
FrontierMath, tiers 1 to 3Not measured45.3%Only DeepSeek V4 Pro 0423 measured
FrontierMath, tier 4Not measured2.4%Only DeepSeek V4 Pro 0423 measured
ProofBenchNot measured16.0%Only DeepSeek V4 Pro 0423 measured
LMArena Text: math14261443DeepSeek V4 Pro 0423
LMArena Text: mathematical work14321455DeepSeek V4 Pro 0423
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
Knowledge benchmarks for DeepSeek V4 Flash 0423 and DeepSeek V4 Pro 0423
BenchmarkDeepSeek V4 Flash 0423DeepSeek V4 Pro 0423Leader
MMLU ProNot measured87.3%Only DeepSeek V4 Pro 0423 measured
LegalBench (Vals AI)Not measured80.3%Only DeepSeek V4 Pro 0423 measured
CaseLaw (Vals AI)Not measured59.4%Only DeepSeek V4 Pro 0423 measured
CorpFin (Vals AI)Not measured61.4%Only DeepSeek V4 Pro 0423 measured
TaxEval (Vals AI)Not measured72.1%Only DeepSeek V4 Pro 0423 measured
MedCode (Vals AI)Not measured40.5%Only DeepSeek V4 Pro 0423 measured
SimpleQA VerifiedNot measured47.0%Only DeepSeek V4 Pro 0423 measured
LMArena Text: science14461470DeepSeek V4 Pro 0423
LMArena Text: medicine and healthcare14481466DeepSeek V4 Pro 0423
LMArena Text: legal and government14391464DeepSeek V4 Pro 0423
LMArena Text: business and finance14251443DeepSeek V4 Pro 0423
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index17
Web design benchmarks for DeepSeek V4 Flash 0423 and DeepSeek V4 Pro 0423
BenchmarkDeepSeek V4 Flash 0423DeepSeek V4 Pro 0423Leader
Design Arena: websites12081235DeepSeek V4 Pro 0423
Design Arena: UI components11641221DeepSeek V4 Pro 0423
Design Arena: game dev11971229DeepSeek V4 Pro 0423
Design Arena: data viz11271203DeepSeek V4 Pro 0423
Design Arena: 3D11891254DeepSeek V4 Pro 0423
Design Arena: all code categories12051240DeepSeek V4 Pro 0423
Design Arena: SVG11551139DeepSeek V4 Flash 0423
Design Arena: ASCII art11091148DeepSeek V4 Pro 0423
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index019
General benchmarks for DeepSeek V4 Flash 0423 and DeepSeek V4 Pro 0423
BenchmarkDeepSeek V4 Flash 0423DeepSeek V4 Pro 0423Leader
Public Benefits Bench (Vals AI)Not measured62.9%Only DeepSeek V4 Pro 0423 measured
MedScribe (Vals AI)Not measured75.1%Only DeepSeek V4 Pro 0423 measured
DTBench86.4%90.7%DeepSeek V4 Pro 0423
LMCA35.9%41.2%DeepSeek V4 Pro 0423
Surface Evolver BenchNot measured40.0%Only DeepSeek V4 Pro 0423 measured
CL-bench LifeNot measured13.5%Only DeepSeek V4 Pro 0423 measured
LMArena Text14321451DeepSeek V4 Pro 0423
LMArena Text: instruction following14211445DeepSeek V4 Pro 0423
LMArena Text: creative writing14031446DeepSeek V4 Pro 0423
LMArena Text: English14411459DeepSeek V4 Pro 0423
LMArena Text: non-English14191439DeepSeek V4 Pro 0423
LMArena Text: Chinese14631481DeepSeek V4 Pro 0423
LMArena Text: German14191458DeepSeek V4 Pro 0423
LMArena Text: Japanese13891446DeepSeek V4 Pro 0423
LMArena Text: Korean13831409DeepSeek V4 Pro 0423
LMArena Text: French14391473DeepSeek V4 Pro 0423
LMArena Text: Spanish14361457DeepSeek V4 Pro 0423
LMArena Text: Russian14271453DeepSeek V4 Pro 0423
LMArena Text: Polish14361461DeepSeek V4 Pro 0423
LMArena Text: multi-turn14491468DeepSeek V4 Pro 0423
LMArena Text: longer queries14341458DeepSeek V4 Pro 0423
LMArena Text: writing and language14101447DeepSeek V4 Pro 0423
LMArena Text: entertainment and media14001431DeepSeek V4 Pro 0423
Neither model has a result on the other 23 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 DeepSeek V4 Pro 0423
BenchmarkDeepSeek V4 Flash 0423DeepSeek V4 Pro 0423Leader
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$0.0002Fits in one request
DeepSeek V4 Pro 0423$0.0019Fits in one request

DeepSeek V4 Flash 0423 costs less

Repository review

50K input + 3K output tokens

DeepSeek V4 Flash 0423$0.0051Fits in one request
DeepSeek V4 Pro 0423$0.053Fits in one request

DeepSeek V4 Flash 0423 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V4 Flash 0423$0.020Fits in one request
DeepSeek V4 Pro 0423$0.210Fits in one request

DeepSeek V4 Flash 0423 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 DeepSeek V4 Pro 0423
SpecificationDeepSeek V4 Flash 0423DeepSeek V4 Pro 0423
MakerDeepSeekDeepSeek
WeightsOpen weightsOpen weights
ReleasedApril 24, 2026April 24, 2026
Context window1.05M1.05M
Input $/Mtok$0.091$0.9553
Output $/Mtok$0.182$1.9105
Coding index54.635.3
Independent measurements behind it11
Cost per solved taskNot computable$0.57
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V4 Flash 0423 better than DeepSeek V4 Pro 0423 for coding?

Pick DeepSeek V4 Flash 0423 for coding: it scores 54.6 on the Vibe Coding Index against 35.3 for DeepSeek V4 Pro 0423. Pick DeepSeek V4 Pro 0423 when what matters is AA Coding Index or WeirdML, where it leads.

Which is cheaper, DeepSeek V4 Flash 0423 or DeepSeek V4 Pro 0423?

DeepSeek V4 Flash 0423 costs $0.091 per million input tokens and $0.182 per million output tokens; DeepSeek V4 Pro 0423 costs $0.9553 and $1.9105. Cost per solved task is known for DeepSeek V4 Pro 0423 only.

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

Neither: both take 1.05M tokens.

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

47 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 DeepSeek V4 Pro 0423's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next