Enter opens the highlighted result. Esc closes.

DeepSeek V3.2 vs GPT-5.4

GPT-5.4 leads DeepSeek V3.2 on coding, 64.4 to 30.0 on the Vibe Coding Index, and DeepSeek V3.2 costs 17.0x less per output token ($0.88 vs $15.00 per million). Updated October 22, 2026; 68 benchmarks have a result for both.

Replace DeepSeek V3.2 Replace GPT-5.4
DeepSeek V3.2DeepSeek
Coding
30.0
Overall
37.9
Output $/M
$0.88
2
GPT-5.4OpenAI
Coding
64.4
Overall
69.6
Output $/M
$15.00
66
vs boards won of 68 shared

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

Pick GPT-5.4 for coding: it scores 64.4 on the Vibe Coding Index against 30.0 for DeepSeek V3.2.

Pick DeepSeek V3.2 for output tokens 17.0x cheaper ($0.88 vs $15.00 per million) and a lower cost per solved task ($0.99 against $1.02).

Model ADeepSeek V3.2DeepSeek30.0/1003 independent benchmarks$0.99 per solved taskModel BGPT-5.4OpenAI64.4/1003 independent benchmarks$1.02 per solved task
Shared results
68
DeepSeek V3.2 only
7
GPT-5.4 only
42
Like-for-like categories
8 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 64.4 from 3 benchmarks.
Widest category
Agentic work, 22.2 points apart on average over 3 shared benchmarks.
Widest single gap
ARC-AGI-2: DeepSeek V3.2 4.0% against GPT-5.4 74.0%, 69.9 points apart on a 0 to 100 scale.
Output price
DeepSeek V3.2 $0.88 against GPT-5.4 $15.00 per million output tokens, 17.0x apart.
Context window
DeepSeek V3.2 takes 164K tokens, GPT-5.4 1.05M.

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-5.4Ties
Coding011
Intelligence02
Agentic work12
Reasoning08
Math03
Knowledge010
Web design17
General023
All shared boards266
CodingLike-for-likeSix of these boards feed the Vibe Coding Index011
Coding benchmarks for DeepSeek V3.2 and GPT-5.4
BenchmarkDeepSeek V3.2GPT-5.4Leader
SWE-bench Verified70.0%Not measuredOnly DeepSeek V3.2 measured
SWE-bench Multilingual59.0%Not measuredOnly DeepSeek V3.2 measured
LMArena WebDev13621464GPT-5.4
AA Coding Index44.271.1GPT-5.4
LiveCodeBench (Vals AI)80.7%84.1%GPT-5.4
SWE-bench Verified (Vals AI)67.6%78.2%GPT-5.4
Vibe Code Bench (Vals AI)5.1%67.4%GPT-5.4
Code migration (Vals AI)Not measured35.0%Only GPT-5.4 measured
ProgramBench (Vals AI)Not measured0.5%Only GPT-5.4 measured
SkillsBench (Vals AI)Not measured51.7%Only GPT-5.4 measured
LiveCodeBench (Artificial Analysis run)86.2%Not measuredOnly DeepSeek V3.2 measured
Terminal-Bench Hard (Artificial Analysis run)35.6%57.6%GPT-5.4
Terminal-Bench39.6%81.8%GPT-5.4
GSO-BenchNot measured31.4%Only GPT-5.4 measured
WeirdMLNot measured77.7%Only GPT-5.4 measured
MirrorCodeNot measured15.6%Only GPT-5.4 measured
ALE-BenchNot measured1607.0Only GPT-5.4 measured
LMArena Text: coding14531496GPT-5.4
LMArena Text: software and IT14491491GPT-5.4
LMArena WebDev: React13501454GPT-5.4
LMArena WebDev: HTML13711478GPT-5.4
LMArena WebDev: from an imageNot measured1436Only GPT-5.4 measured
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
BenchmarkDeepSeek V3.2GPT-5.4Leader
AA Intelligence Index21.539.0GPT-5.4
Epoch Capabilities Index146.1157.3GPT-5.4
Agentic workLike-for-likePublic boards, shown as published, kept out of the index12
Agentic work benchmarks for DeepSeek V3.2 and GPT-5.4
BenchmarkDeepSeek V3.2GPT-5.4Leader
Design Arena: agents building web appsNot measured1059Only GPT-5.4 measured
Design Arena: agents building full-stack appsNot measured1017Only GPT-5.4 measured
Design Arena: agents building mobile appsNot measured1087Only GPT-5.4 measured
Design Arena: agents building Android appsNot measured1031Only GPT-5.4 measured
Design Arena: agents building Godot gamesNot measured1135Only GPT-5.4 measured
τ²-Bench Telecom90.6%87.1%DeepSeek V3.2
APEX-Agents21.3%52.4%GPT-5.4
METR time horizonsNot measured74.3%Only GPT-5.4 measured
DeepResearch BenchNot measured35.1%Only GPT-5.4 measured
PostTrainBenchNot measured19.0%Only GPT-5.4 measured
Vending-Bench 2$1,034$6,144GPT-5.4
Neither model has a result on the other 30 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index08
Reasoning benchmarks for DeepSeek V3.2 and GPT-5.4
BenchmarkDeepSeek V3.2GPT-5.4Leader
GPQA Diamond80.3%91.7%GPT-5.4
MMMU Pro (Vals AI)Not measured87.5%Only GPT-5.4 measured
GPQA Diamond (Artificial Analysis run)84.0%92.0%GPT-5.4
Humanity's Last Exam (Artificial Analysis run)24.6%43.7%GPT-5.4
GPQA Diamond (Epoch AI run)Not measured93.3%Only GPT-5.4 measured
ARC-AGI57.0%93.7%GPT-5.4
ARC-AGI-24.0%74.0%GPT-5.4
Chess puzzlesNot measured48.0%Only GPT-5.4 measured
Mystery game puzzlesNot measured37.0%Only GPT-5.4 measured
EBR-benchNot measured25.4%Only GPT-5.4 measured
LMArena Text: hard prompts14341485GPT-5.4
LMArena Text: expert14361507GPT-5.4
LMArena Text: hard prompts in English14461479GPT-5.4
LMArena Vision: diagramsNot measured1327Only GPT-5.4 measured
LMArena Vision: homeworkNot measured1336Only GPT-5.4 measured
Kagi LLM BenchmarkNot measured63.8%Only GPT-5.4 measured
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for DeepSeek V3.2 and GPT-5.4
BenchmarkDeepSeek V3.2GPT-5.4Leader
AIME84.6%96.7%GPT-5.4
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 measured97.8%Only GPT-5.4 measured
FrontierMath, tiers 1 to 3Not measured78.6%Only GPT-5.4 measured
FrontierMath, tier 4Not measured49.0%Only GPT-5.4 measured
ProofBenchNot measured56.0%Only GPT-5.4 measured
LMArena Text: math14351488GPT-5.4
LMArena Text: mathematical work14401497GPT-5.4
Neither model has a result on the other 3 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index010
Knowledge benchmarks for DeepSeek V3.2 and GPT-5.4
BenchmarkDeepSeek V3.2GPT-5.4Leader
MMLU Pro84.9%87.5%GPT-5.4
LegalBench (Vals AI)76.1%86.0%GPT-5.4
CaseLaw (Vals AI)55.4%63.8%GPT-5.4
CorpFin (Vals AI)51.0%65.3%GPT-5.4
TaxEval (Vals AI)68.2%74.0%GPT-5.4
MortgageTax (Vals AI)Not measured68.3%Only GPT-5.4 measured
MedQA (Vals AI)93.9%96.1%GPT-5.4
MedCode (Vals AI)Not measured41.3%Only GPT-5.4 measured
MMLU Pro (Artificial Analysis run)86.2%Not measuredOnly DeepSeek V3.2 measured
SimpleQA VerifiedNot measured45.1%Only GPT-5.4 measured
LMArena Text: science14461479GPT-5.4
LMArena Text: medicine and healthcare14401458GPT-5.4
LMArena Text: legal and government14251486GPT-5.4
LMArena Text: business and finance14101474GPT-5.4
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index17
Web design benchmarks for DeepSeek V3.2 and GPT-5.4
BenchmarkDeepSeek V3.2GPT-5.4Leader
Design Arena: websites11751198GPT-5.4
Design Arena: UI components11461212GPT-5.4
Design Arena: game dev11311194GPT-5.4
Design Arena: data viz11581196GPT-5.4
Design Arena: 3D11321065DeepSeek V3.2
Design Arena: all code categories11631179GPT-5.4
Design Arena: SVG10321141GPT-5.4
Design Arena: ASCII art10831188GPT-5.4
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index023
General benchmarks for DeepSeek V3.2 and GPT-5.4
BenchmarkDeepSeek V3.2GPT-5.4Leader
SAGE (Vals AI)Not measured43.3%Only GPT-5.4 measured
MedScribe (Vals AI)Not measured77.5%Only GPT-5.4 measured
IFBench60.7%73.9%GPT-5.4
Long context reasoning (AA-LCR)73.3%82.0%GPT-5.4
DTBench85.6%94.4%GPT-5.4
LMCA28.8%52.0%GPT-5.4
CL-bench12.4%27.9%GPT-5.4
Furniture assemblyNot measured37.5%Only GPT-5.4 measured
CL-bench Life7.4%21.7%GPT-5.4
LMArena Text14251469GPT-5.4
LMArena Text: instruction following14131469GPT-5.4
LMArena Text: creative writing14001439GPT-5.4
LMArena VisionNot measured1303Only GPT-5.4 measured
LMArena Text: English14391467GPT-5.4
LMArena Text: non-English14091465GPT-5.4
LMArena Text: Chinese14551520GPT-5.4
LMArena Text: German14131472GPT-5.4
LMArena Text: Japanese13741485GPT-5.4
LMArena Text: Korean13701449GPT-5.4
LMArena Text: French14291493GPT-5.4
LMArena Text: Spanish14241452GPT-5.4
LMArena Text: Russian14241480GPT-5.4
LMArena Text: Polish14191472GPT-5.4
LMArena Text: multi-turn14271482GPT-5.4
LMArena Text: longer queries14281473GPT-5.4
LMArena Text: writing and language14071458GPT-5.4
LMArena Text: entertainment and media13951438GPT-5.4
LMArena Vision: EnglishNot measured1301Only GPT-5.4 measured
LMArena Vision: ChineseNot measured1354Only GPT-5.4 measured
LMArena Vision: reading textNot measured1312Only GPT-5.4 measured
LMArena Vision: humorNot measured1284Only GPT-5.4 measured
LMArena Vision: recognizing thingsNot measured1251Only GPT-5.4 measured
LMArena Vision: creative writingNot measured1283Only GPT-5.4 measured
LMArena DocumentNot measured1471Only GPT-5.4 measured
Neither model has a result on the other 12 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
BenchmarkDeepSeek V3.2GPT-5.4Leader
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$0.010Fits 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$0.170Fits 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$0.650Fits 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
SpecificationDeepSeek V3.2OpenAI GPT-5.4
MakerDeepSeekOpenAI
WeightsOpen weightsNo public weights listed
ReleasedDecember 1, 2025March 5, 2026
Context window164K1.05M
Input $/Mtok$0.29$2.50
Output $/Mtok$0.88$15.00
Coding index30.064.4
Independent measurements behind it33
Cost per solved task$0.99$1.02
SourceOpenRouter listingOpenRouter listing

Questions

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

Pick GPT-5.4 for coding: it scores 64.4 on the Vibe Coding Index against 30.0 for DeepSeek V3.2. Pick DeepSeek V3.2 for output tokens 17.0x cheaper ($0.88 vs $15.00 per million) and a lower cost per solved task ($0.99 against $1.02).

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

DeepSeek V3.2 costs $0.29 per million input tokens and $0.88 per million output tokens; GPT-5.4 costs $2.50 and $15.00. Per solved SWE-bench Verified task, DeepSeek V3.2 costs $0.99 and GPT-5.4 $1.02.

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

GPT-5.4, with 1.05M tokens against 164K.

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

68 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's on 3. 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" title="DeepSeek V3.2 vs GPT-5.4, 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">LLMBenchmark.ai, DeepSeek V3.2 vs GPT-5.4</a></p>