Enter opens the highlighted result. Esc closes.

DeepSeek V3.2 vs GPT-5.4 Mini

GPT-5.4 Mini leads DeepSeek V3.2 on coding, 35.8 to 30.0 on the Vibe Coding Index, and DeepSeek V3.2 costs 5.1x less per output token ($0.88 vs $4.50 per million). Updated October 22, 2026; 53 benchmarks have a result for both.

Replace DeepSeek V3.2 Replace GPT-5.4 Mini
DeepSeek V3.2DeepSeek
Coding
30.0
Overall
37.9
Output $/M
$0.88
27
GPT-5.4 MiniOpenAI
Coding
35.8
Overall
44.0
Output $/M
$4.50
26
vs boards won of 53 shared

DeepSeek V3.2 or GPT-5.4 Mini: which to pick

Pick GPT-5.4 Mini for coding: it scores 35.8 on the Vibe Coding Index against 30.0 for DeepSeek V3.2.

Pick DeepSeek V3.2 for output tokens 5.1x cheaper ($0.88 vs $4.50 per million) and work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.

Model ADeepSeek V3.2DeepSeek30.0/1003 independent benchmarks$0.99 per solved taskModel BGPT-5.4 MiniOpenAI35.8/1005 independent benchmarks$0.70 per solved task
Shared results
53
DeepSeek V3.2 only
22
GPT-5.4 Mini only
36
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, GPT-5.4 Mini 35.8 from 5 benchmarks.
Widest category
Coding, 10.2 points apart on average over 10 shared benchmarks.
Widest single gap
Vibe Code Bench (Vals AI): DeepSeek V3.2 5.1% against GPT-5.4 Mini 48.0%, 42.9 points apart on a 0 to 100 scale.
Output price
DeepSeek V3.2 $0.88 against GPT-5.4 Mini $4.50 per million output tokens, 5.1x apart.
Context window
DeepSeek V3.2 takes 164K tokens, GPT-5.4 Mini 400K.

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 V3.2BarsGPT-5.4 MiniTies
Coding28
Intelligence02
Agentic work10
Reasoning35
Math21
Knowledge53
General147
All shared boards2726
CodingLike-for-likeSix of these boards feed the Vibe Coding Index28
Coding benchmarks for DeepSeek V3.2 and GPT-5.4 Mini
BenchmarkDeepSeek V3.2GPT-5.4 MiniLeader
SWE-bench Verified70.0%Not measuredOnly DeepSeek V3.2 measured
SWE-bench Multilingual59.0%Not measuredOnly DeepSeek V3.2 measured
LMArena WebDev13621397GPT-5.4 Mini
AA Coding Index44.256.1GPT-5.4 Mini
LiveCodeBench (Vals AI)80.7%81.5%GPT-5.4 Mini
SWE-bench Verified (Vals AI)67.6%73.0%GPT-5.4 Mini
Terminal-Bench 4 (Vals AI)Not measured2.5%Only GPT-5.4 Mini measured
Vibe Code Bench (Vals AI)5.1%48.0%GPT-5.4 Mini
Code migration (Vals AI)Not measured12.9%Only GPT-5.4 Mini measured
ProgramBench (Vals AI)Not measured0.0%Only GPT-5.4 Mini measured
Terminal-Bench 2.1 (Vals AI)Not measured54.7%Only GPT-5.4 Mini measured
LiveCodeBench (Artificial Analysis run)86.2%Not measuredOnly DeepSeek V3.2 measured
SciCodeNot measured52.1%Only GPT-5.4 Mini measured
Terminal-Bench Hard (Artificial Analysis run)35.6%52.3%GPT-5.4 Mini
Terminal-Bench39.6%Not measuredOnly DeepSeek V3.2 measured
FrontierCodeNot measured27.0%Only GPT-5.4 Mini measured
WeirdMLNot measured60.3%Only GPT-5.4 Mini measured
ALE-BenchNot measured1188.6Only GPT-5.4 Mini measured
LMArena Text: coding14531438DeepSeek V3.2
LMArena Text: software and IT14491436DeepSeek V3.2
LMArena WebDev: React13501386GPT-5.4 Mini
LMArena WebDev: HTML13711419GPT-5.4 Mini
Neither model has a result on the other 17 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for DeepSeek V3.2 and GPT-5.4 Mini
BenchmarkDeepSeek V3.2GPT-5.4 MiniLeader
AA Intelligence Index21.524.1GPT-5.4 Mini
Epoch Capabilities Index146.1148.7GPT-5.4 Mini
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for DeepSeek V3.2 and GPT-5.4 Mini
BenchmarkDeepSeek V3.2GPT-5.4 MiniLeader
AA Agentic IndexNot measured17.9Only GPT-5.4 Mini measured
Finance Agent (Vals AI)Not measured45.4%Only GPT-5.4 Mini measured
Tax Agent Bench (Vals AI)Not measured8.8%Only GPT-5.4 Mini measured
Legal Research Bench (Vals AI)Not measured12.5%Only GPT-5.4 Mini measured
Excel Modeling Benchmark (Vals AI)Not measured45.4%Only GPT-5.4 Mini measured
τ²-Bench Telecom90.6%83.3%DeepSeek V3.2
APEX-Agents21.3%Not measuredOnly DeepSeek V3.2 measured
DeepResearch BenchNot measured36.3%Only GPT-5.4 Mini measured
Vending-Bench 2$1,034Not measuredOnly DeepSeek V3.2 measured
Neither model has a result on the other 32 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index35
Reasoning benchmarks for DeepSeek V3.2 and GPT-5.4 Mini
BenchmarkDeepSeek V3.2GPT-5.4 MiniLeader
GPQA Diamond80.3%83.1%GPT-5.4 Mini
MMMU Pro (Vals AI)Not measured79.3%Only GPT-5.4 Mini measured
GPQA Diamond (Artificial Analysis run)84.0%87.5%GPT-5.4 Mini
Humanity's Last Exam (Artificial Analysis run)24.6%28.1%GPT-5.4 Mini
GPQA Diamond (Epoch AI run)Not measured86.9%Only GPT-5.4 Mini measured
ARC-AGI57.0%63.7%GPT-5.4 Mini
ARC-AGI-24.0%18.9%GPT-5.4 Mini
Chess puzzlesNot measured23.0%Only GPT-5.4 Mini measured
Mystery game puzzlesNot measured11.0%Only GPT-5.4 Mini measured
LMArena Text: hard prompts14341424DeepSeek V3.2
LMArena Text: expert14361435DeepSeek V3.2
LMArena Text: hard prompts in English14461420DeepSeek V3.2
LMArena Vision: diagramsNot measured1266Only GPT-5.4 Mini measured
LMArena Vision: homeworkNot measured1285Only GPT-5.4 Mini measured
Kagi LLM BenchmarkNot measured37.9%Only GPT-5.4 Mini measured
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index21
Math benchmarks for DeepSeek V3.2 and GPT-5.4 Mini
BenchmarkDeepSeek V3.2GPT-5.4 MiniLeader
AIME84.6%95.6%GPT-5.4 Mini
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
OTIS Mock AIMENot measured88.9%Only GPT-5.4 Mini measured
FrontierMath, tiers 1 to 3Not measured51.2%Only GPT-5.4 Mini measured
FrontierMath, tier 4Not measured9.8%Only GPT-5.4 Mini measured
ProofBenchNot measured21.0%Only GPT-5.4 Mini measured
LMArena Text: math14351418DeepSeek V3.2
LMArena Text: mathematical work14401429DeepSeek V3.2
Neither model has a result on the other 3 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index53
Knowledge benchmarks for DeepSeek V3.2 and GPT-5.4 Mini
BenchmarkDeepSeek V3.2GPT-5.4 MiniLeader
MMLU Pro84.9%84.5%DeepSeek V3.2
LegalBench (Vals AI)76.1%Not measuredOnly DeepSeek V3.2 measured
CaseLaw (Vals AI)55.4%51.7%DeepSeek V3.2
CorpFin (Vals AI)51.0%60.9%GPT-5.4 Mini
TaxEval (Vals AI)68.2%71.2%GPT-5.4 Mini
MortgageTax (Vals AI)Not measured63.5%Only GPT-5.4 Mini 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
SimpleQA VerifiedNot measured29.4%Only GPT-5.4 Mini measured
LMArena Text: science14461417DeepSeek V3.2
LMArena Text: medicine and healthcare14401395DeepSeek V3.2
LMArena Text: legal and government14251414DeepSeek V3.2
LMArena Text: business and finance14101418GPT-5.4 Mini
Neither model has a result on the other 5 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 GPT-5.4 Mini
BenchmarkDeepSeek V3.2GPT-5.4 MiniLeader
Design Arena: websites1175Not measuredOnly DeepSeek V3.2 measured
Design Arena: UI components1146Not measuredOnly DeepSeek V3.2 measured
Design Arena: game dev1131Not measuredOnly DeepSeek V3.2 measured
Design Arena: data viz1158Not measuredOnly DeepSeek V3.2 measured
Design Arena: 3D1132Not measuredOnly DeepSeek V3.2 measured
Design Arena: all code categories1163Not 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 index147
General benchmarks for DeepSeek V3.2 and GPT-5.4 Mini
BenchmarkDeepSeek V3.2GPT-5.4 MiniLeader
SAGE (Vals AI)Not measured50.8%Only GPT-5.4 Mini measured
Vals Multimodal IndexNot measured54.2%Only GPT-5.4 Mini measured
IFBench60.7%73.3%GPT-5.4 Mini
Long context reasoning (AA-LCR)73.3%77.0%GPT-5.4 Mini
DTBench85.6%80.0%DeepSeek V3.2
LMCA28.8%40.8%GPT-5.4 Mini
CL-bench12.4%Not measuredOnly DeepSeek V3.2 measured
CL-bench Life7.4%Not measuredOnly DeepSeek V3.2 measured
LMArena Text14251412DeepSeek V3.2
LMArena Text: instruction following14131405DeepSeek V3.2
LMArena Text: creative writing14001370DeepSeek V3.2
LMArena VisionNot measured1245Only GPT-5.4 Mini measured
LMArena Text: English14391412DeepSeek V3.2
LMArena Text: non-English14091405DeepSeek V3.2
LMArena Text: Chinese14551446DeepSeek V3.2
LMArena Text: German14131408DeepSeek V3.2
LMArena Text: Japanese13741375GPT-5.4 Mini
LMArena Text: Korean13701370GPT-5.4 Mini
LMArena Text: French14291441GPT-5.4 Mini
LMArena Text: Spanish14241405DeepSeek V3.2
LMArena Text: Russian14241417DeepSeek V3.2
LMArena Text: Polish14191415DeepSeek V3.2
LMArena Text: multi-turn14271429GPT-5.4 Mini
LMArena Text: longer queries14281408DeepSeek V3.2
LMArena Text: writing and language14071393DeepSeek V3.2
LMArena Text: entertainment and media13951373DeepSeek V3.2
LMArena Vision: EnglishNot measured1244Only GPT-5.4 Mini measured
LMArena Vision: ChineseNot measured1286Only GPT-5.4 Mini measured
LMArena Vision: reading textNot measured1253Only GPT-5.4 Mini measured
LMArena Vision: humorNot measured1235Only GPT-5.4 Mini measured
LMArena Vision: recognizing thingsNot measured1218Only GPT-5.4 Mini measured
LMArena Vision: creative writingNot measured1222Only GPT-5.4 Mini measured
Neither model has a result on the other 14 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 GPT-5.4 Mini
BenchmarkDeepSeek V3.2GPT-5.4 MiniLeader
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
GPT-5.4 Mini$0.0030Fits in one request

DeepSeek V3.2 costs less

Repository review

50K input + 3K output tokens

DeepSeek V3.2$0.017Fits in one request
GPT-5.4 Mini$0.051Fits in one request

DeepSeek V3.2 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V3.2$0.067Exceeds the context window
GPT-5.4 Mini$0.195Fits in one request

DeepSeek V3.2 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 GPT-5.4 Mini
SpecificationDeepSeek V3.2OpenAI GPT-5.4 Mini
MakerDeepSeekOpenAI
WeightsOpen weightsNo public weights listed
ReleasedDecember 1, 2025March 17, 2026
Context window164K400K
Input $/Mtok$0.29$0.75
Output $/Mtok$0.88$4.50
Coding index30.035.8
Independent measurements behind it35
Cost per solved task$0.99$0.70
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V3.2 better than GPT-5.4 Mini for coding?

Pick GPT-5.4 Mini for coding: it scores 35.8 on the Vibe Coding Index against 30.0 for DeepSeek V3.2. Pick DeepSeek V3.2 for output tokens 5.1x cheaper ($0.88 vs $4.50 per million) and work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.

Which is cheaper, DeepSeek V3.2 or GPT-5.4 Mini?

DeepSeek V3.2 costs $0.29 per million input tokens and $0.88 per million output tokens; GPT-5.4 Mini costs $0.75 and $4.50. Per solved SWE-bench Verified task, DeepSeek V3.2 costs $0.99 and GPT-5.4 Mini $0.70.

Which has the bigger context window, DeepSeek V3.2 or GPT-5.4 Mini?

GPT-5.4 Mini, with 400K tokens against 164K.

How many benchmarks is the DeepSeek V3.2 vs GPT-5.4 Mini comparison based on?

53 benchmarks have a result for both models as of October 22, 2026. DeepSeek V3.2's coding index rests on 3 independent benchmarks and GPT-5.4 Mini's on 5. Where only one model has a result, the page says so instead of naming a winner.

Compare next

Embed this comparison on your site

Free under CC BY 4.0, while the source link stays visible. Preview the frame · Terms and other embeds

<iframe src="https://llmbenchmark.ai/embed/compare/deepseek-v3-2-vs-gpt-5-4-mini" title="DeepSeek V3.2 vs GPT-5.4 Mini, LLMBenchmark.ai" width="100%" height="360" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/compare/deepseek-v3-2-vs-gpt-5-4-mini">LLMBenchmark.ai, DeepSeek V3.2 vs GPT-5.4 Mini</a></p>