Enter opens the highlighted result. Esc closes.

DeepSeek V3.2 Exp vs o1

DeepSeek V3.2 Exp leads o1 on the Artificial Analysis Intelligence Index, 16.6 to 15.2, and DeepSeek V3.2 Exp costs 146.3x less per output token ($0.41 vs $60.00 per million). Updated October 21, 2026; 42 benchmarks have a result for both.

Replace DeepSeek V3.2 Exp Replace o1
DeepSeek V3.2 ExpDeepSeek
Coding
No data
Overall
No data
Output $/M
$0.41
36
o1OpenAI
Coding
No data
Overall
44.6
Output $/M
$60.00
5
vs boards won of 42 shared, 1 tied

DeepSeek V3.2 Exp or o1: which to pick

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

Pick DeepSeek V3.2 Exp for output tokens 146.3x cheaper ($0.41 vs $60.00 per million) and work measured by WeirdML or τ²-Bench Telecom, where it leads.

Model ADeepSeek V3.2 ExpDeepSeekNot benchmarked1 independent benchmarkNo cost per solved taskModel Bo1OpenAINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
42
DeepSeek V3.2 Exp only
17
o1 only
27
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 Exp not benchmarked, o1 not benchmarked.
Widest category
Agentic work, 28.7 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: DeepSeek V3.2 Exp 33.9% against o1 62.6%, 28.7 points apart on a 0 to 100 scale.
Output price
DeepSeek V3.2 Exp $0.41 against o1 $60.00 per million output tokens, 146.3x apart.
Context window
DeepSeek V3.2 Exp takes 164K tokens, o1 200K.

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 V3.2 ExpBarso1Ties
Coding51
Intelligence20
Agentic work01
Reasoning50
Math20
Knowledge50
General1731 tie
All shared boards3651 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index51
Coding benchmarks for DeepSeek V3.2 Exp and o1
BenchmarkDeepSeek V3.2 Expo1Leader
Aider polyglot74.2%61.7%DeepSeek V3.2 Exp
LMArena WebDev1272Not measuredOnly DeepSeek V3.2 Exp measured
AA Coding IndexNot measured39.7Only o1 measured
LiveCodeBench (Vals AI)Not measured50.3%Only o1 measured
LiveCodeBench (Artificial Analysis run)78.9%67.9%DeepSeek V3.2 Exp
Terminal-Bench Hard (Artificial Analysis run)31.1%12.9%DeepSeek V3.2 Exp
WeirdML39.5%46.1%o1
LMArena Text: coding14381367DeepSeek V3.2 Exp
LMArena Text: software and IT14381366DeepSeek V3.2 Exp
LMArena WebDev: HTML1281Not measuredOnly DeepSeek V3.2 Exp measured
SciCodeNot measured4.6%Only o1 measured
Neither model has a result on the other 28 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for DeepSeek V3.2 Exp and o1
BenchmarkDeepSeek V3.2 Expo1Leader
AA Intelligence Index16.615.2DeepSeek V3.2 Exp
Epoch Capabilities Index144.9141.7DeepSeek V3.2 Exp
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for DeepSeek V3.2 Exp and o1
BenchmarkDeepSeek V3.2 Expo1Leader
τ²-Bench Telecom33.9%62.6%o1
METR time horizonsNot measured51.1%Only o1 measured
TheAgentCompany42.9%Not measuredOnly DeepSeek V3.2 Exp measured
Berkeley Function Calling Leaderboard (BFCL)56.7%Not measuredOnly DeepSeek V3.2 Exp measured
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index50
Reasoning benchmarks for DeepSeek V3.2 Exp and o1
BenchmarkDeepSeek V3.2 Expo1Leader
GPQA DiamondNot measured73.2%Only o1 measured
MMMU Pro (Vals AI)Not measured77.4%Only o1 measured
GPQA Diamond (Artificial Analysis run)79.7%74.7%DeepSeek V3.2 Exp
Humanity's Last Exam (Artificial Analysis run)14.9%7.0%DeepSeek V3.2 Exp
GPQA Diamond (Epoch AI run)Not measured76.8%Only o1 measured
ARC-AGINot measured30.7%Only o1 measured
SimpleBenchNot measured40.1%Only o1 measured
Chess puzzlesNot measured10.0%Only o1 measured
VPCTNot measured37.0%Only o1 measured
LMArena Text: hard prompts14291371DeepSeek V3.2 Exp
LMArena Text: expert14221361DeepSeek V3.2 Exp
LMArena Text: hard prompts in English14441372DeepSeek V3.2 Exp
Kagi LLM Benchmark52.2%Not measuredOnly DeepSeek V3.2 Exp measured
Neither model has a result on the other 9 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index20
Math benchmarks for DeepSeek V3.2 Exp and o1
BenchmarkDeepSeek V3.2 Expo1Leader
AIMENot measured71.5%Only o1 measured
MATH 500 (Vals AI)Not measured90.4%Only o1 measured
MGSM (Vals AI)Not measured89.3%Only o1 measured
AA Math Index87.7Not measuredOnly DeepSeek V3.2 Exp measured
AIME 2025 (Artificial Analysis run)87.7%Not measuredOnly DeepSeek V3.2 Exp measured
OTIS Mock AIMENot measured73.3%Only o1 measured
FrontierMath, tiers 1 to 3Not measured14.7%Only o1 measured
MATH level 5Not measured94.7%Only o1 measured
LMArena Text: math14221388DeepSeek V3.2 Exp
LMArena Text: mathematical work14331390DeepSeek V3.2 Exp
Neither model has a result on the other 3 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
Knowledge benchmarks for DeepSeek V3.2 Exp and o1
BenchmarkDeepSeek V3.2 Expo1Leader
MMLU ProNot measured83.5%Only o1 measured
LegalBench (Vals AI)Not measured80.4%Only o1 measured
TaxEval (Vals AI)Not measured74.3%Only o1 measured
MedQA (Vals AI)Not measured96.5%Only o1 measured
MMLU Pro (Artificial Analysis run)85.0%84.1%DeepSeek V3.2 Exp
SimpleQA VerifiedNot measured41.1%Only o1 measured
GeoBenchNot measured80.0%Only o1 measured
LMArena Text: science14431369DeepSeek V3.2 Exp
LMArena Text: medicine and healthcare14681355DeepSeek V3.2 Exp
LMArena Text: legal and government14191368DeepSeek V3.2 Exp
LMArena Text: business and finance14121328DeepSeek V3.2 Exp
Neither model has a result on the other 7 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Web design benchmarks for DeepSeek V3.2 Exp and o1
BenchmarkDeepSeek V3.2 Expo1Leader
Design Arena: websites1179Not measuredOnly DeepSeek V3.2 Exp measured
Design Arena: UI components1167Not measuredOnly DeepSeek V3.2 Exp measured
Design Arena: game dev1144Not measuredOnly DeepSeek V3.2 Exp measured
Design Arena: data viz1152Not measuredOnly DeepSeek V3.2 Exp measured
Design Arena: 3D1148Not measuredOnly DeepSeek V3.2 Exp measured
Design Arena: all code categories1171Not measuredOnly DeepSeek V3.2 Exp measured
Design Arena: SVG1032Not measuredOnly DeepSeek V3.2 Exp measured
Neither model has a result on the other 2 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index173
General benchmarks for DeepSeek V3.2 Exp and o1
BenchmarkDeepSeek V3.2 Expo1Leader
IFBench54.1%70.3%o1
Long context reasoning (AA-LCR)72.3%65.0%DeepSeek V3.2 Exp
DTBench87.7%74.7%DeepSeek V3.2 Exp
LMCA29.1%22.3%DeepSeek V3.2 Exp
Fiction.LiveBench83.3%83.3%Tie
Creative writing (Lech Mazur)Not measured70.2%Only o1 measured
CL-bench13.2%Not measuredOnly DeepSeek V3.2 Exp measured
CL-bench Life9.5%Not measuredOnly DeepSeek V3.2 Exp measured
LMArena Text14251366DeepSeek V3.2 Exp
LMArena Text: instruction following14011367DeepSeek V3.2 Exp
LMArena Text: creative writing14041347DeepSeek V3.2 Exp
LMArena VisionNot measured1168Only o1 measured
LMArena Text: English14411372DeepSeek V3.2 Exp
LMArena Text: non-English14041358DeepSeek V3.2 Exp
LMArena Text: Chinese14611394DeepSeek V3.2 Exp
LMArena Text: German14401337DeepSeek V3.2 Exp
LMArena Text: Japanese13311346o1
LMArena Text: Korean13721396o1
LMArena Text: French14341344DeepSeek V3.2 Exp
LMArena Text: Spanish14411345DeepSeek V3.2 Exp
LMArena Text: Russian14121356DeepSeek V3.2 Exp
LMArena Text: Polish1435Not measuredOnly DeepSeek V3.2 Exp measured
LMArena Text: multi-turn14221355DeepSeek V3.2 Exp
LMArena Text: longer queries14181378DeepSeek V3.2 Exp
LMArena Text: writing and language14071360DeepSeek V3.2 Exp
LMArena Text: entertainment and media14071358DeepSeek V3.2 Exp
LMArena Vision: EnglishNot measured1162Only o1 measured
LMArena Vision: ChineseNot measured1235Only o1 measured
Neither model has a result on the other 18 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for DeepSeek V3.2 Exp and o1
BenchmarkDeepSeek V3.2 Expo1Leader
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 Exp$0.0005Fits in one request
o1$0.045Fits in one request

DeepSeek V3.2 Exp costs less

Repository review

50K input + 3K output tokens

DeepSeek V3.2 Exp$0.015Fits in one request
o1$0.930Fits in one request

DeepSeek V3.2 Exp costs less

Agent loop

200K input + 10K output tokens

DeepSeek V3.2 Exp$0.058Exceeds the context window
o1$3.60Exceeds the context window

DeepSeek V3.2 Exp 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 Exp and o1
SpecificationDeepSeek V3.2 ExpOpenAI o1
MakerDeepSeekOpenAI
WeightsOpen weightsNo public weights listed
ReleasedSeptember 29, 2025December 17, 2024
Context window164K200K
Input $/Mtok$0.27$15.00
Output $/Mtok$0.41$60.00
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it10
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V3.2 Exp better than o1 for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick DeepSeek V3.2 Exp for output tokens 146.3x cheaper ($0.41 vs $60.00 per million) and work measured by WeirdML or τ²-Bench Telecom, where it leads.

Which is cheaper, DeepSeek V3.2 Exp or o1?

DeepSeek V3.2 Exp costs $0.27 per million input tokens and $0.41 per million output tokens; o1 costs $15.00 and $60.00. Cost per solved task is known for neither of them.

Which has the bigger context window, DeepSeek V3.2 Exp or o1?

o1, with 200K tokens against 164K.

How many benchmarks is the DeepSeek V3.2 Exp vs o1 comparison based on?

42 benchmarks have a result for both models as of October 21, 2026. DeepSeek V3.2 Exp's coding index rests on 1 independent benchmark and o1's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next