Enter opens the highlighted result. Esc closes.

DeepSeek V3.2 vs DeepSeek V4 Flash 0423

DeepSeek V4 Flash 0423 leads DeepSeek V3.2 on the Artificial Analysis Intelligence Index, 24.4 to 21.5, and DeepSeek V4 Flash 0423 costs 3.1x less per output token ($0.28 vs $0.88 per million). Updated October 22, 2026; 44 benchmarks have a result for both.

Replace DeepSeek V3.2 Replace DeepSeek V4 Flash 0423
DeepSeek V3.2DeepSeek
Coding
30.0
Overall
37.9
Output $/M
$0.88
3
DeepSeek V4 Flash 0423DeepSeek
Coding
No data
Overall
No data
Output $/M
$0.28
41
vs boards won of 44 shared

DeepSeek V3.2 or DeepSeek V4 Flash 0423: which to pick

Only DeepSeek V3.2 has a coding score, 30.0 on the Vibe Coding Index; DeepSeek V4 Flash 0423 has none, so the two cannot be ranked on coding.

Pick DeepSeek V4 Flash 0423 for output tokens 3.1x cheaper ($0.28 vs $0.88 per million) and a larger context window (1.05M against 164K tokens).

Model ADeepSeek V3.2DeepSeek30.0/1003 independent benchmarks$0.99 per solved taskModel BDeepSeek V4 Flash 0423DeepSeekNot benchmarked1 independent benchmarkNo cost per solved task
Shared results
44
DeepSeek V3.2 only
31
DeepSeek V4 Flash 0423 only
5
Like-for-like categories
7 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 V3.2 30.0 from 3 benchmarks, DeepSeek V4 Flash 0423 not benchmarked.
Widest category
Coding, 18.5 points apart on average over 6 shared benchmarks.
Widest single gap
LMArena WebDev: React: DeepSeek V3.2 1350 against DeepSeek V4 Flash 0423 1585, 39.2 points apart on a 0 to 100 scale.
Output price
DeepSeek V3.2 $0.88 against DeepSeek V4 Flash 0423 $0.28 per million output tokens, 3.1x apart.
Context window
DeepSeek V3.2 takes 164K tokens, DeepSeek V4 Flash 0423 1.05M.

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 V3.2BarsDeepSeek V4 Flash 0423Ties
Coding06
Intelligence02
Reasoning03
Math20
Knowledge04
Web design17
General019
All shared boards341
CodingLike-for-likeSix of these boards feed the Vibe Coding Index06
Coding benchmarks for DeepSeek V3.2 and DeepSeek V4 Flash 0423
BenchmarkDeepSeek V3.2DeepSeek V4 Flash 0423Leader
SWE-bench Verified70.0%Not measuredOnly DeepSeek V3.2 measured
SWE-bench Multilingual59.0%Not measuredOnly DeepSeek V3.2 measured
LMArena WebDev13621582DeepSeek V4 Flash 0423
AA Coding Index44.252.0DeepSeek V4 Flash 0423
LiveCodeBench (Vals AI)80.7%Not measuredOnly DeepSeek V3.2 measured
SWE-bench Verified (Vals AI)67.6%Not measuredOnly DeepSeek V3.2 measured
Vibe Code Bench (Vals AI)5.1%Not measuredOnly DeepSeek V3.2 measured
LiveCodeBench (Artificial Analysis run)86.2%Not measuredOnly DeepSeek V3.2 measured
Terminal-Bench Hard (Artificial Analysis run)35.6%Not measuredOnly DeepSeek V3.2 measured
Terminal-Bench39.6%Not measuredOnly DeepSeek V3.2 measured
WeirdMLNot measured45.6%Only DeepSeek V4 Flash 0423 measured
ALE-BenchNot measured678.2Only DeepSeek V4 Flash 0423 measured
LMArena Text: coding14531457DeepSeek V4 Flash 0423
LMArena Text: software and IT14491453DeepSeek V4 Flash 0423
LMArena WebDev: React13501585DeepSeek V4 Flash 0423
LMArena WebDev: HTML13711558DeepSeek V4 Flash 0423
Neither model has a result on the other 23 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for DeepSeek V3.2 and DeepSeek V4 Flash 0423
BenchmarkDeepSeek V3.2DeepSeek V4 Flash 0423Leader
AA Intelligence Index21.524.4DeepSeek V4 Flash 0423
Epoch Capabilities Index146.1146.1DeepSeek V4 Flash 0423
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
Agentic work benchmarks for DeepSeek V3.2 and DeepSeek V4 Flash 0423
BenchmarkDeepSeek V3.2DeepSeek V4 Flash 0423Leader
AA Agentic IndexNot measured26.3Only DeepSeek V4 Flash 0423 measured
τ²-Bench Telecom90.6%Not measuredOnly DeepSeek V3.2 measured
APEX-Agents21.3%Not measuredOnly DeepSeek V3.2 measured
Vending-Bench 2$1,034Not measuredOnly DeepSeek V3.2 measured
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index03
Reasoning benchmarks for DeepSeek V3.2 and DeepSeek V4 Flash 0423
BenchmarkDeepSeek V3.2DeepSeek V4 Flash 0423Leader
GPQA Diamond80.3%Not measuredOnly DeepSeek V3.2 measured
GPQA Diamond (Artificial Analysis run)84.0%Not measuredOnly DeepSeek V3.2 measured
Humanity's Last Exam (Artificial Analysis run)24.6%Not measuredOnly DeepSeek V3.2 measured
ARC-AGI57.0%Not measuredOnly DeepSeek V3.2 measured
ARC-AGI-24.0%Not measuredOnly DeepSeek V3.2 measured
SimpleBenchNot measured46.3%Only DeepSeek V4 Flash 0423 measured
LMArena Text: hard prompts14341444DeepSeek V4 Flash 0423
LMArena Text: expert14361441DeepSeek V4 Flash 0423
LMArena Text: hard prompts in English14461449DeepSeek V4 Flash 0423
Kagi LLM BenchmarkNot measured52.2%Only DeepSeek V4 Flash 0423 measured
Neither model has a result on the other 12 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index20
Math benchmarks for DeepSeek V3.2 and DeepSeek V4 Flash 0423
BenchmarkDeepSeek V3.2DeepSeek V4 Flash 0423Leader
AIME84.6%Not measuredOnly DeepSeek V3.2 measured
MGSM (Vals AI)86.0%Not measuredOnly DeepSeek V3.2 measured
AA Math Index92.0Not measuredOnly DeepSeek V3.2 measured
AIME 2025 (Artificial Analysis run)92.0%Not measuredOnly DeepSeek V3.2 measured
LMArena Text: math14351426DeepSeek V3.2
LMArena Text: mathematical work14401432DeepSeek V3.2
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 V3.2 and DeepSeek V4 Flash 0423
BenchmarkDeepSeek V3.2DeepSeek V4 Flash 0423Leader
MMLU Pro84.9%Not measuredOnly DeepSeek V3.2 measured
LegalBench (Vals AI)76.1%Not measuredOnly DeepSeek V3.2 measured
CaseLaw (Vals AI)55.4%Not measuredOnly DeepSeek V3.2 measured
CorpFin (Vals AI)51.0%Not measuredOnly DeepSeek V3.2 measured
TaxEval (Vals AI)68.2%Not measuredOnly DeepSeek V3.2 measured
MedQA (Vals AI)93.9%Not measuredOnly DeepSeek V3.2 measured
MMLU Pro (Artificial Analysis run)86.2%Not measuredOnly DeepSeek V3.2 measured
LMArena Text: science14461446DeepSeek V4 Flash 0423
LMArena Text: medicine and healthcare14401448DeepSeek V4 Flash 0423
LMArena Text: legal and government14251439DeepSeek V4 Flash 0423
LMArena Text: business and finance14101425DeepSeek V4 Flash 0423
Neither model has a result on the other 7 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index17
Web design benchmarks for DeepSeek V3.2 and DeepSeek V4 Flash 0423
BenchmarkDeepSeek V3.2DeepSeek V4 Flash 0423Leader
Design Arena: websites11751207DeepSeek V4 Flash 0423
Design Arena: UI components11461162DeepSeek V4 Flash 0423
Design Arena: game dev11311196DeepSeek V4 Flash 0423
Design Arena: data viz11581127DeepSeek V3.2
Design Arena: 3D11321188DeepSeek V4 Flash 0423
Design Arena: all code categories11631205DeepSeek V4 Flash 0423
Design Arena: SVG10321155DeepSeek V4 Flash 0423
Design Arena: ASCII art10831109DeepSeek V4 Flash 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 V3.2 and DeepSeek V4 Flash 0423
BenchmarkDeepSeek V3.2DeepSeek V4 Flash 0423Leader
IFBench60.7%Not measuredOnly DeepSeek V3.2 measured
Long context reasoning (AA-LCR)73.3%Not measuredOnly DeepSeek V3.2 measured
DTBench85.6%86.4%DeepSeek V4 Flash 0423
LMCA28.8%35.9%DeepSeek V4 Flash 0423
CL-bench12.4%Not measuredOnly DeepSeek V3.2 measured
CL-bench Life7.4%Not measuredOnly DeepSeek V3.2 measured
LMArena Text14251432DeepSeek V4 Flash 0423
LMArena Text: instruction following14131421DeepSeek V4 Flash 0423
LMArena Text: creative writing14001403DeepSeek V4 Flash 0423
LMArena Text: English14391441DeepSeek V4 Flash 0423
LMArena Text: non-English14091419DeepSeek V4 Flash 0423
LMArena Text: Chinese14551463DeepSeek V4 Flash 0423
LMArena Text: German14131419DeepSeek V4 Flash 0423
LMArena Text: Japanese13741389DeepSeek V4 Flash 0423
LMArena Text: Korean13701383DeepSeek V4 Flash 0423
LMArena Text: French14291439DeepSeek V4 Flash 0423
LMArena Text: Spanish14241436DeepSeek V4 Flash 0423
LMArena Text: Russian14241427DeepSeek V4 Flash 0423
LMArena Text: Polish14191436DeepSeek V4 Flash 0423
LMArena Text: multi-turn14271449DeepSeek V4 Flash 0423
LMArena Text: longer queries14281434DeepSeek V4 Flash 0423
LMArena Text: writing and language14071410DeepSeek V4 Flash 0423
LMArena Text: entertainment and media13951400DeepSeek V4 Flash 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 V3.2 and DeepSeek V4 Flash 0423
BenchmarkDeepSeek V3.2DeepSeek V4 Flash 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 V3.2$0.0007Fits in one request
DeepSeek V4 Flash 0423$0.0003Fits in one request

DeepSeek V4 Flash 0423 costs less

Repository review

50K input + 3K output tokens

DeepSeek V3.2$0.017Fits in one request
DeepSeek V4 Flash 0423$0.0078Fits in one request

DeepSeek V4 Flash 0423 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V3.2$0.067Exceeds the context window
DeepSeek V4 Flash 0423$0.031Fits 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 V3.2 and DeepSeek V4 Flash 0423
SpecificationDeepSeek V3.2DeepSeek V4 Flash 0423
MakerDeepSeekDeepSeek
WeightsOpen weightsOpen weights
ReleasedDecember 1, 2025April 24, 2026
Context window164K1.05M
Input $/Mtok$0.29$0.14
Output $/Mtok$0.88$0.28
Coding index30.0Not benchmarked
Independent measurements behind it31
Cost per solved task$0.99Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V3.2 better than DeepSeek V4 Flash 0423 for coding?

Only DeepSeek V3.2 has a coding score, 30.0 on the Vibe Coding Index; DeepSeek V4 Flash 0423 has none, so the two cannot be ranked on coding. Pick DeepSeek V4 Flash 0423 for output tokens 3.1x cheaper ($0.28 vs $0.88 per million) and a larger context window (1.05M against 164K tokens).

Which is cheaper, DeepSeek V3.2 or DeepSeek V4 Flash 0423?

DeepSeek V3.2 costs $0.29 per million input tokens and $0.88 per million output tokens; DeepSeek V4 Flash 0423 costs $0.14 and $0.28. Cost per solved task is known for DeepSeek V3.2 only.

Which has the bigger context window, DeepSeek V3.2 or DeepSeek V4 Flash 0423?

DeepSeek V4 Flash 0423, with 1.05M tokens against 164K.

How many benchmarks is the DeepSeek V3.2 vs DeepSeek V4 Flash 0423 comparison based on?

44 benchmarks have a result for both models as of October 22, 2026. DeepSeek V3.2's coding index rests on 3 independent benchmarks and DeepSeek V4 Flash 0423's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next