Enter opens the highlighted result. Esc closes.

DeepSeek V3.2 vs Step 3.5 Flash

DeepSeek V3.2 leads Step 3.5 Flash on the Artificial Analysis Intelligence Index, 21.5 to 17.0, and Step 3.5 Flash costs 2.9x less per output token ($0.30 vs $0.88 per million). Updated October 21, 2026; 35 benchmarks have a result for both.

Replace DeepSeek V3.2 Replace Step 3.5 Flash
DeepSeek V3.2DeepSeek
Coding
30.0
Overall
37.9
Output $/M
$0.88
33
Step 3.5 FlashStepFun
Coding
No data
Overall
No data
Output $/M
$0.30
2
vs boards won of 35 shared

DeepSeek V3.2 or Step 3.5 Flash: which to pick

Only DeepSeek V3.2 has a coding score, 30.0 on the Vibe Coding Index; Step 3.5 Flash has none, so the two cannot be ranked on coding.

Pick Step 3.5 Flash for output tokens 2.9x cheaper ($0.30 vs $0.88 per million) and a larger context window (262K against 164K tokens).

Model ADeepSeek V3.2DeepSeek30.0/1003 independent benchmarks$0.99 per solved taskModel BStep 3.5 FlashStepFunNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
35
DeepSeek V3.2 only
40
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 30.0 from 3 benchmarks, Step 3.5 Flash not benchmarked.
Widest category
Intelligence, 4.5 points apart on average over 1 shared benchmark.
Widest single gap
Long context reasoning (AA-LCR): DeepSeek V3.2 73.3% against Step 3.5 Flash 63.0%, 10.3 points apart on a 0 to 100 scale.
Output price
DeepSeek V3.2 $0.88 against Step 3.5 Flash $0.30 per million output tokens, 2.9x apart.
Context window
DeepSeek V3.2 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 V3.2BarsStep 3.5 FlashTies
Coding30
Intelligence10
Agentic work01
Reasoning50
Math20
Knowledge40
General181
All shared boards332
CodingLike-for-likeSix of these boards feed the Vibe Coding Index30
Coding benchmarks for DeepSeek V3.2 and Step 3.5 Flash
BenchmarkDeepSeek V3.2Step 3.5 FlashLeader
SWE-bench Verified70.0%Not measuredOnly DeepSeek V3.2 measured
SWE-bench Multilingual59.0%Not measuredOnly DeepSeek V3.2 measured
LMArena WebDev1362Not measuredOnly DeepSeek V3.2 measured
AA Coding Index44.2Not measuredOnly DeepSeek V3.2 measured
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%32.6%DeepSeek V3.2
Terminal-Bench39.6%Not measuredOnly DeepSeek V3.2 measured
LMArena Text: coding14531436DeepSeek V3.2
LMArena Text: software and IT14491434DeepSeek V3.2
LMArena WebDev: React1350Not measuredOnly DeepSeek V3.2 measured
LMArena WebDev: HTML1371Not measuredOnly DeepSeek V3.2 measured
Neither model has a result on the other 25 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for DeepSeek V3.2 and Step 3.5 Flash
BenchmarkDeepSeek V3.2Step 3.5 FlashLeader
AA Intelligence Index21.517.0DeepSeek V3.2
Epoch Capabilities Index146.1Not measuredOnly DeepSeek V3.2 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for DeepSeek V3.2 and Step 3.5 Flash
BenchmarkDeepSeek V3.2Step 3.5 FlashLeader
τ²-Bench Telecom90.6%94.4%Step 3.5 Flash
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 38 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index50
Reasoning benchmarks for DeepSeek V3.2 and Step 3.5 Flash
BenchmarkDeepSeek V3.2Step 3.5 FlashLeader
GPQA Diamond80.3%Not measuredOnly DeepSeek V3.2 measured
GPQA Diamond (Artificial Analysis run)84.0%83.1%DeepSeek V3.2
Humanity's Last Exam (Artificial Analysis run)24.6%24.5%DeepSeek V3.2
ARC-AGI57.0%Not measuredOnly DeepSeek V3.2 measured
ARC-AGI-24.0%Not measuredOnly DeepSeek V3.2 measured
LMArena Text: hard prompts14341411DeepSeek V3.2
LMArena Text: expert14361421DeepSeek V3.2
LMArena Text: hard prompts in English14461421DeepSeek V3.2
Neither model has a result on the other 14 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index20
Math benchmarks for DeepSeek V3.2 and Step 3.5 Flash
BenchmarkDeepSeek V3.2Step 3.5 FlashLeader
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: math14351408DeepSeek V3.2
LMArena Text: mathematical work14401421DeepSeek V3.2
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
Knowledge benchmarks for DeepSeek V3.2 and Step 3.5 Flash
BenchmarkDeepSeek V3.2Step 3.5 FlashLeader
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: science14461415DeepSeek V3.2
LMArena Text: medicine and healthcare14401408DeepSeek V3.2
LMArena Text: legal and government14251408DeepSeek V3.2
LMArena Text: business and finance14101394DeepSeek V3.2
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 V3.2 and Step 3.5 Flash
BenchmarkDeepSeek V3.2Step 3.5 FlashLeader
Design Arena: websites1175Not measuredOnly DeepSeek V3.2 measured
Design Arena: UI components1149Not measuredOnly DeepSeek V3.2 measured
Design Arena: game dev1132Not measuredOnly DeepSeek V3.2 measured
Design Arena: data viz1158Not measuredOnly DeepSeek V3.2 measured
Design Arena: 3D1133Not measuredOnly DeepSeek V3.2 measured
Design Arena: all code categories1164Not measuredOnly DeepSeek V3.2 measured
Design Arena: SVG1032Not measuredOnly DeepSeek V3.2 measured
Design Arena: ASCII art1083Not measuredOnly 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 index181
General benchmarks for DeepSeek V3.2 and Step 3.5 Flash
BenchmarkDeepSeek V3.2Step 3.5 FlashLeader
IFBench60.7%66.5%Step 3.5 Flash
Long context reasoning (AA-LCR)73.3%63.0%DeepSeek V3.2
DTBench85.6%Not measuredOnly DeepSeek V3.2 measured
LMCA28.8%Not measuredOnly DeepSeek V3.2 measured
CL-bench12.4%Not measuredOnly DeepSeek V3.2 measured
CL-bench Life7.4%Not measuredOnly DeepSeek V3.2 measured
LMArena Text14251403DeepSeek V3.2
LMArena Text: instruction following14131385DeepSeek V3.2
LMArena Text: creative writing14001357DeepSeek V3.2
LMArena Text: English14391417DeepSeek V3.2
LMArena Text: non-English14091385DeepSeek V3.2
LMArena Text: Chinese14551446DeepSeek V3.2
LMArena Text: German14131405DeepSeek V3.2
LMArena Text: Japanese13741353DeepSeek V3.2
LMArena Text: Korean13701351DeepSeek V3.2
LMArena Text: French14291421DeepSeek V3.2
LMArena Text: Spanish14241419DeepSeek V3.2
LMArena Text: Russian14241385DeepSeek V3.2
LMArena Text: Polish14191389DeepSeek V3.2
LMArena Text: multi-turn14271404DeepSeek V3.2
LMArena Text: longer queries14281402DeepSeek V3.2
LMArena Text: writing and language14071372DeepSeek V3.2
LMArena Text: entertainment and media13951360DeepSeek V3.2
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 Step 3.5 Flash
BenchmarkDeepSeek V3.2Step 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$0.0007Fits 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$0.017Fits 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$0.067Exceeds 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 and Step 3.5 Flash
SpecificationDeepSeek V3.2StepFun Step 3.5 Flash
MakerDeepSeekStepFun
WeightsOpen weightsOpen weights
ReleasedDecember 1, 2025January 29, 2026
Context window164K262K
Input $/Mtok$0.29$0.10
Output $/Mtok$0.88$0.30
Coding index30.0Not benchmarked
Independent measurements behind it30
Cost per solved task$0.99Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V3.2 better than Step 3.5 Flash for coding?

Only DeepSeek V3.2 has a coding score, 30.0 on the Vibe Coding Index; Step 3.5 Flash has none, so the two cannot be ranked on coding. Pick Step 3.5 Flash for output tokens 2.9x cheaper ($0.30 vs $0.88 per million) and a larger context window (262K against 164K tokens).

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

DeepSeek V3.2 costs $0.29 per million input tokens and $0.88 per million output tokens; Step 3.5 Flash costs $0.10 and $0.30. Cost per solved task is known for DeepSeek V3.2 only.

Which has the bigger context window, DeepSeek V3.2 or Step 3.5 Flash?

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

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

35 benchmarks have a result for both models as of October 21, 2026. DeepSeek V3.2's coding index rests on 3 independent benchmarks 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