Enter opens the highlighted result. Esc closes.

DeepSeek V3 0324 vs DeepSeek V3.2

DeepSeek V3.2 leads DeepSeek V3 0324 on the Artificial Analysis Intelligence Index, 21.5 to 9.7, and DeepSeek V3.2 costs 1.2x less per output token ($0.88 vs $1.07 per million). Updated October 22, 2026; 24 benchmarks have a result for both.

Replace DeepSeek V3 0324 Replace DeepSeek V3.2
DeepSeek V3 0324DeepSeek
Coding
No data
Overall
No data
Output $/M
$1.07
4
DeepSeek V3.2DeepSeek
Coding
30.0
Overall
37.9
Output $/M
$0.88
20
vs boards won of 24 shared

DeepSeek V3 0324 or DeepSeek V3.2: which to pick

Only DeepSeek V3.2 has a coding score, 30.0 on the Vibe Coding Index; DeepSeek V3 0324 has none, so the two cannot be ranked on coding.

Pick DeepSeek V3 0324 for work measured by MGSM (Vals AI) or LegalBench (Vals AI), where it leads.

Model ADeepSeek V3 0324DeepSeekNot benchmarkedNo coding benchmarkNo cost per solved taskModel BDeepSeek V3.2DeepSeek30.0/1003 independent benchmarks$0.99 per solved task
Shared results
24
DeepSeek V3 0324 only
11
DeepSeek V3.2 only
51
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 0324 not benchmarked, DeepSeek V3.2 30.0 from 3 benchmarks.
Widest category
Agentic work, 43.6 points apart on average over 1 shared benchmark.
Widest single gap
AA Math Index: DeepSeek V3 0324 41.0 against DeepSeek V3.2 92.0, 51.0 points apart on a 0 to 100 scale.
Output price
DeepSeek V3 0324 $1.07 against DeepSeek V3.2 $0.88 per million output tokens, 1.2x apart.
Context window
Both take 164K 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 V3 0324BarsDeepSeek V3.2Ties
Coding05
Intelligence01
Agentic work01
Reasoning03
Math13
Knowledge33
General04
All shared boards420
CodingLike-for-likeSix of these boards feed the Vibe Coding Index05
Coding benchmarks for DeepSeek V3 0324 and DeepSeek V3.2
BenchmarkDeepSeek V3 0324DeepSeek V3.2Leader
SWE-bench Verified42.0%70.0%DeepSeek V3.2
SWE-bench MultilingualNot measured59.0%Only DeepSeek V3.2 measured
LMArena WebDevNot measured1362Only DeepSeek V3.2 measured
AA Coding Index21.244.2DeepSeek V3.2
LiveCodeBench (Vals AI)65.5%80.7%DeepSeek V3.2
SWE-bench Verified (Vals AI)Not measured67.6%Only DeepSeek V3.2 measured
Vibe Code Bench (Vals AI)Not measured5.1%Only DeepSeek V3.2 measured
LiveCodeBench (Artificial Analysis run)40.5%86.2%DeepSeek V3.2
SciCode39.0%Not measuredOnly DeepSeek V3 0324 measured
Terminal-Bench Hard (Artificial Analysis run)15.2%35.6%DeepSeek V3.2
Terminal-BenchNot measured39.6%Only DeepSeek V3.2 measured
WeirdML36.1%Not measuredOnly DeepSeek V3 0324 measured
LMArena Text: codingNot measured1453Only DeepSeek V3.2 measured
LMArena Text: software and ITNot measured1449Only DeepSeek V3.2 measured
LMArena WebDev: ReactNot measured1350Only DeepSeek V3.2 measured
LMArena WebDev: HTMLNot measured1371Only DeepSeek V3.2 measured
Neither model has a result on the other 23 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for DeepSeek V3 0324 and DeepSeek V3.2
BenchmarkDeepSeek V3 0324DeepSeek V3.2Leader
AA Intelligence Index9.721.5DeepSeek V3.2
Epoch Capabilities IndexNot measured146.1Only DeepSeek V3.2 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for DeepSeek V3 0324 and DeepSeek V3.2
BenchmarkDeepSeek V3 0324DeepSeek V3.2Leader
AA Agentic Index0.8Not measuredOnly DeepSeek V3 0324 measured
τ²-Bench Telecom47.1%90.6%DeepSeek V3.2
APEX-AgentsNot measured21.3%Only DeepSeek V3.2 measured
METR time horizons49.6%Not measuredOnly DeepSeek V3 0324 measured
Vending-Bench 2Not measured$1,034Only DeepSeek V3.2 measured
Neither model has a result on the other 36 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index03
Reasoning benchmarks for DeepSeek V3 0324 and DeepSeek V3.2
BenchmarkDeepSeek V3 0324DeepSeek V3.2Leader
GPQA Diamond61.6%80.3%DeepSeek V3.2
GPQA Diamond (Artificial Analysis run)65.5%84.0%DeepSeek V3.2
Humanity's Last Exam (Artificial Analysis run)4.7%24.6%DeepSeek V3.2
GPQA Diamond (Epoch AI run)67.6%Not measuredOnly DeepSeek V3 0324 measured
ARC-AGINot measured57.0%Only DeepSeek V3.2 measured
ARC-AGI-2Not measured4.0%Only DeepSeek V3.2 measured
SimpleBench27.2%Not measuredOnly DeepSeek V3 0324 measured
LMArena Text: hard promptsNot measured1434Only DeepSeek V3.2 measured
LMArena Text: expertNot measured1436Only DeepSeek V3.2 measured
LMArena Text: hard prompts in EnglishNot measured1446Only DeepSeek V3.2 measured
Neither model has a result on the other 12 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index13
Math benchmarks for DeepSeek V3 0324 and DeepSeek V3.2
BenchmarkDeepSeek V3 0324DeepSeek V3.2Leader
AIME52.2%84.6%DeepSeek V3.2
MATH 500 (Vals AI)88.6%Not measuredOnly DeepSeek V3 0324 measured
MGSM (Vals AI)91.7%86.0%DeepSeek V3 0324
AA Math Index41.092.0DeepSeek V3.2
AIME 2025 (Artificial Analysis run)41.0%92.0%DeepSeek V3.2
OTIS Mock AIME37.8%Not measuredOnly DeepSeek V3 0324 measured
MATH level 575.5%Not measuredOnly DeepSeek V3 0324 measured
LMArena Text: mathNot measured1435Only DeepSeek V3.2 measured
LMArena Text: mathematical workNot measured1440Only DeepSeek V3.2 measured
Neither model has a result on the other 4 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index33
Knowledge benchmarks for DeepSeek V3 0324 and DeepSeek V3.2
BenchmarkDeepSeek V3 0324DeepSeek V3.2Leader
MMLU Pro79.5%84.9%DeepSeek V3.2
LegalBench (Vals AI)77.7%76.1%DeepSeek V3 0324
CaseLaw (Vals AI)Not measured55.4%Only DeepSeek V3.2 measured
CorpFin (Vals AI)54.7%51.0%DeepSeek V3 0324
TaxEval (Vals AI)71.1%68.2%DeepSeek V3 0324
MedQA (Vals AI)82.0%93.9%DeepSeek V3.2
MMLU Pro (Artificial Analysis run)81.9%86.2%DeepSeek V3.2
LMArena Text: scienceNot measured1446Only DeepSeek V3.2 measured
LMArena Text: medicine and healthcareNot measured1440Only DeepSeek V3.2 measured
LMArena Text: legal and governmentNot measured1425Only DeepSeek V3.2 measured
LMArena Text: business and financeNot measured1410Only DeepSeek V3.2 measured
Neither model has a result on the other 7 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for DeepSeek V3 0324 and DeepSeek V3.2
BenchmarkDeepSeek V3 0324DeepSeek V3.2Leader
Design Arena: websitesNot measured1175Only DeepSeek V3.2 measured
Design Arena: UI componentsNot measured1146Only DeepSeek V3.2 measured
Design Arena: game devNot measured1131Only DeepSeek V3.2 measured
Design Arena: data vizNot measured1158Only DeepSeek V3.2 measured
Design Arena: 3DNot measured1132Only DeepSeek V3.2 measured
Design Arena: all code categoriesNot measured1163Only DeepSeek V3.2 measured
Design Arena: SVGNot measured1032Only DeepSeek V3.2 measured
Design Arena: ASCII artNot measured1083Only DeepSeek V3.2 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index04
General benchmarks for DeepSeek V3 0324 and DeepSeek V3.2
BenchmarkDeepSeek V3 0324DeepSeek V3.2Leader
IFBench41.0%60.7%DeepSeek V3.2
Long context reasoning (AA-LCR)40.7%73.3%DeepSeek V3.2
DTBench64.8%85.6%DeepSeek V3.2
LMCA15.5%28.8%DeepSeek V3.2
Fiction.LiveBench50.0%Not measuredOnly DeepSeek V3 0324 measured
Creative writing (Lech Mazur)77.0%Not measuredOnly DeepSeek V3 0324 measured
CL-benchNot measured12.4%Only DeepSeek V3.2 measured
CL-bench LifeNot measured7.4%Only DeepSeek V3.2 measured
LMArena TextNot measured1425Only DeepSeek V3.2 measured
LMArena Text: instruction followingNot measured1413Only DeepSeek V3.2 measured
LMArena Text: creative writingNot measured1400Only DeepSeek V3.2 measured
LMArena Text: EnglishNot measured1439Only DeepSeek V3.2 measured
LMArena Text: non-EnglishNot measured1409Only DeepSeek V3.2 measured
LMArena Text: ChineseNot measured1455Only DeepSeek V3.2 measured
LMArena Text: GermanNot measured1413Only DeepSeek V3.2 measured
LMArena Text: JapaneseNot measured1374Only DeepSeek V3.2 measured
LMArena Text: KoreanNot measured1370Only DeepSeek V3.2 measured
LMArena Text: FrenchNot measured1429Only DeepSeek V3.2 measured
LMArena Text: SpanishNot measured1424Only DeepSeek V3.2 measured
LMArena Text: RussianNot measured1424Only DeepSeek V3.2 measured
LMArena Text: PolishNot measured1419Only DeepSeek V3.2 measured
LMArena Text: multi-turnNot measured1427Only DeepSeek V3.2 measured
LMArena Text: longer queriesNot measured1428Only DeepSeek V3.2 measured
LMArena Text: writing and languageNot measured1407Only DeepSeek V3.2 measured
LMArena Text: entertainment and mediaNot measured1395Only DeepSeek V3.2 measured
Neither model has a result on the other 21 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for DeepSeek V3 0324 and DeepSeek V3.2
BenchmarkDeepSeek V3 0324DeepSeek V3.2Leader
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 0324$0.0008Fits in one request
DeepSeek V3.2$0.0007Fits in one request

DeepSeek V3.2 costs less

Repository review

50K input + 3K output tokens

DeepSeek V3 0324$0.017Fits in one request
DeepSeek V3.2$0.017Fits in one request

DeepSeek V3 0324 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V3 0324$0.065Exceeds the context window
DeepSeek V3.2$0.067Exceeds the context window

DeepSeek V3 0324 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 0324 and DeepSeek V3.2
SpecificationDeepSeek V3 0324DeepSeek V3.2
MakerDeepSeekDeepSeek
WeightsOpen weightsOpen weights
ReleasedMarch 24, 2025December 1, 2025
Context window164K164K
Input $/Mtok$0.27$0.29
Output $/Mtok$1.07$0.88
Coding indexNot benchmarked30.0
Independent measurements behind it03
Cost per solved taskNot computable$0.99
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V3 0324 better than DeepSeek V3.2 for coding?

Only DeepSeek V3.2 has a coding score, 30.0 on the Vibe Coding Index; DeepSeek V3 0324 has none, so the two cannot be ranked on coding. Pick DeepSeek V3 0324 for work measured by MGSM (Vals AI) or LegalBench (Vals AI), where it leads.

Which is cheaper, DeepSeek V3 0324 or DeepSeek V3.2?

DeepSeek V3 0324 costs $0.27 per million input tokens and $1.07 per million output tokens; DeepSeek V3.2 costs $0.29 and $0.88. Cost per solved task is known for DeepSeek V3.2 only.

Which has the bigger context window, DeepSeek V3 0324 or DeepSeek V3.2?

Neither: both take 164K tokens.

How many benchmarks is the DeepSeek V3 0324 vs DeepSeek V3.2 comparison based on?

24 benchmarks have a result for both models as of October 22, 2026. DeepSeek V3 0324's coding index rests on 0 independent benchmarks and DeepSeek V3.2's on 3. Where only one model has a result, the page says so instead of naming a winner.

Compare next