Enter opens the highlighted result. Esc closes.

DeepSeek V3.2 Exp vs Step 3.5 Flash

Step 3.5 Flash leads DeepSeek V3.2 Exp on the Artificial Analysis Intelligence Index, 17.0 to 16.6, and Step 3.5 Flash costs 1.4x less per output token ($0.30 vs $0.41 per million). Updated October 21, 2026; 35 benchmarks have a result for both.

Replace DeepSeek V3.2 Exp Replace Step 3.5 Flash
DeepSeek V3.2 ExpDeepSeek
Coding
No data
Overall
16.6
Output $/M
$0.41
28
Step 3.5 FlashStepFun
Coding
No data
Overall
17.0
Output $/M
$0.30
7
vs boards won of 35 shared

DeepSeek V3.2 Exp 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 V3.2 Exp for work measured by Terminal-Bench Hard (Artificial Analysis run) or AA Intelligence Index, where it leads.

Model ADeepSeek V3.2 ExpDeepSeekNot benchmarked1 independent benchmarkNo cost per solved taskModel BStep 3.5 FlashStepFunNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
35
DeepSeek V3.2 Exp only
22
Step 3.5 Flash only
0
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, Step 3.5 Flash not benchmarked.
Widest category
Agentic work, 60.5 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: DeepSeek V3.2 Exp 33.9% against Step 3.5 Flash 94.4%, 60.5 points apart on a 0 to 100 scale.
Output price
DeepSeek V3.2 Exp $0.41 against Step 3.5 Flash $0.30 per million output tokens, 1.4x apart.
Context window
DeepSeek V3.2 Exp takes 164K 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 V3.2 ExpBarsStep 3.5 FlashTies
Coding21
Intelligence01
Agentic work01
Reasoning32
Math20
Knowledge40
General172
All shared boards287
CodingLike-for-likeSix of these boards feed the Vibe Coding Index21
Coding benchmarks for DeepSeek V3.2 Exp and Step 3.5 Flash
BenchmarkDeepSeek V3.2 ExpStep 3.5 FlashLeader
Aider polyglot74.2%Not measuredOnly DeepSeek V3.2 Exp measured
LMArena WebDev1272Not measuredOnly DeepSeek V3.2 Exp measured
LiveCodeBench (Artificial Analysis run)78.9%Not measuredOnly DeepSeek V3.2 Exp measured
Terminal-Bench Hard (Artificial Analysis run)31.1%32.6%Step 3.5 Flash
WeirdML39.5%Not measuredOnly DeepSeek V3.2 Exp measured
LMArena Text: coding14381436DeepSeek V3.2 Exp
LMArena Text: software and IT14381434DeepSeek V3.2 Exp
LMArena WebDev: HTML1281Not measuredOnly DeepSeek V3.2 Exp measured
Neither model has a result on the other 30 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for DeepSeek V3.2 Exp and Step 3.5 Flash
BenchmarkDeepSeek V3.2 ExpStep 3.5 FlashLeader
AA Intelligence Index16.617.0Step 3.5 Flash
Epoch Capabilities Index144.9Not measuredOnly DeepSeek V3.2 Exp measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for DeepSeek V3.2 Exp and Step 3.5 Flash
BenchmarkDeepSeek V3.2 ExpStep 3.5 FlashLeader
τ²-Bench Telecom33.9%94.4%Step 3.5 Flash
TheAgentCompany42.9%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 index32
Reasoning benchmarks for DeepSeek V3.2 Exp and Step 3.5 Flash
BenchmarkDeepSeek V3.2 ExpStep 3.5 FlashLeader
GPQA Diamond (Artificial Analysis run)79.7%83.1%Step 3.5 Flash
Humanity's Last Exam (Artificial Analysis run)14.9%24.5%Step 3.5 Flash
LMArena Text: hard prompts14291411DeepSeek V3.2 Exp
LMArena Text: expert14221421DeepSeek V3.2 Exp
LMArena Text: hard prompts in English14441421DeepSeek V3.2 Exp
Neither model has a result on the other 16 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index20
Math benchmarks for DeepSeek V3.2 Exp and Step 3.5 Flash
BenchmarkDeepSeek V3.2 ExpStep 3.5 FlashLeader
AA Math Index87.7Not measuredOnly DeepSeek V3.2 Exp measured
AIME 2025 (Artificial Analysis run)87.7%Not measuredOnly DeepSeek V3.2 Exp measured
LMArena Text: math14221408DeepSeek V3.2 Exp
LMArena Text: mathematical work14331421DeepSeek V3.2 Exp
Neither model has a result on the other 9 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
Knowledge benchmarks for DeepSeek V3.2 Exp and Step 3.5 Flash
BenchmarkDeepSeek V3.2 ExpStep 3.5 FlashLeader
MMLU Pro (Artificial Analysis run)85.0%Not measuredOnly DeepSeek V3.2 Exp measured
LMArena Text: science14431415DeepSeek V3.2 Exp
LMArena Text: medicine and healthcare14681408DeepSeek V3.2 Exp
LMArena Text: legal and government14191408DeepSeek V3.2 Exp
LMArena Text: business and finance14121394DeepSeek V3.2 Exp
Neither model has a result on the other 12 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 Step 3.5 Flash
BenchmarkDeepSeek V3.2 ExpStep 3.5 FlashLeader
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 index172
General benchmarks for DeepSeek V3.2 Exp and Step 3.5 Flash
BenchmarkDeepSeek V3.2 ExpStep 3.5 FlashLeader
IFBench54.1%66.5%Step 3.5 Flash
Long context reasoning (AA-LCR)72.3%63.0%DeepSeek V3.2 Exp
DTBench87.7%Not measuredOnly DeepSeek V3.2 Exp measured
LMCA29.1%Not measuredOnly DeepSeek V3.2 Exp measured
Fiction.LiveBench83.3%Not measuredOnly DeepSeek V3.2 Exp measured
CL-bench13.2%Not measuredOnly DeepSeek V3.2 Exp measured
CL-bench Life9.5%Not measuredOnly DeepSeek V3.2 Exp measured
LMArena Text14251403DeepSeek V3.2 Exp
LMArena Text: instruction following14011385DeepSeek V3.2 Exp
LMArena Text: creative writing14041357DeepSeek V3.2 Exp
LMArena Text: English14411417DeepSeek V3.2 Exp
LMArena Text: non-English14041385DeepSeek V3.2 Exp
LMArena Text: Chinese14611446DeepSeek V3.2 Exp
LMArena Text: German14401405DeepSeek V3.2 Exp
LMArena Text: Japanese13311353Step 3.5 Flash
LMArena Text: Korean13721351DeepSeek V3.2 Exp
LMArena Text: French14341421DeepSeek V3.2 Exp
LMArena Text: Spanish14411419DeepSeek V3.2 Exp
LMArena Text: Russian14121385DeepSeek V3.2 Exp
LMArena Text: Polish14351389DeepSeek V3.2 Exp
LMArena Text: multi-turn14221404DeepSeek V3.2 Exp
LMArena Text: longer queries14181402DeepSeek V3.2 Exp
LMArena Text: writing and language14071372DeepSeek V3.2 Exp
LMArena Text: entertainment and media14071360DeepSeek V3.2 Exp
Neither model has a result on the other 22 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 Step 3.5 Flash
BenchmarkDeepSeek V3.2 ExpStep 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 V3.2 Exp$0.0005Fits 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 V3.2 Exp$0.015Fits 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 V3.2 Exp$0.058Exceeds the context window
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 V3.2 Exp and Step 3.5 Flash
SpecificationDeepSeek V3.2 ExpStepFun Step 3.5 Flash
MakerDeepSeekStepFun
WeightsOpen weightsOpen weights
ReleasedSeptember 29, 2025January 29, 2026
Context window164K262K
Input $/Mtok$0.27$0.10
Output $/Mtok$0.41$0.30
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 Step 3.5 Flash for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick DeepSeek V3.2 Exp for work measured by Terminal-Bench Hard (Artificial Analysis run) or AA Intelligence Index, where it leads.

Which is cheaper, DeepSeek V3.2 Exp or Step 3.5 Flash?

DeepSeek V3.2 Exp costs $0.27 per million input tokens and $0.41 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 V3.2 Exp or Step 3.5 Flash?

Step 3.5 Flash, with 262K tokens against 164K.

How many benchmarks is the DeepSeek V3.2 Exp vs Step 3.5 Flash comparison based on?

35 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 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