Enter opens the highlighted result. Esc closes.

DeepSeek V4 Pro 0423 vs GPT-5.4

GPT-5.4 leads DeepSeek V4 Pro 0423 on coding, 64.4 to 38.7 on the Vibe Coding Index, and DeepSeek V4 Pro 0423 costs 5.0x less per output token ($2.976 vs $15.00 per million). Updated October 22, 2026; 74 benchmarks have a result for both.

Replace DeepSeek V4 Pro 0423 Replace GPT-5.4
DeepSeek V4 Pro 0423DeepSeek
Coding
38.7
Overall
50.0
Output $/M
$2.976
11
GPT-5.4OpenAI
Coding
64.4
Overall
69.6
Output $/M
$15.00
63
vs boards won of 74 shared

DeepSeek V4 Pro 0423 or GPT-5.4: which to pick

Pick GPT-5.4 for coding: it scores 64.4 on the Vibe Coding Index against 38.7 for DeepSeek V4 Pro 0423, though on 3 benchmarks against 5.

Pick DeepSeek V4 Pro 0423 for output tokens 5.0x cheaper ($2.976 vs $15.00 per million) and a lower cost per solved task ($0.57 against $1.02).

Model ADeepSeek V4 Pro 0423DeepSeek38.7/1005 independent benchmarks$0.57 per solved taskModel BGPT-5.4OpenAI64.4/1003 independent benchmarks$1.02 per solved task
Shared results
74
DeepSeek V4 Pro 0423 only
10
GPT-5.4 only
36
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 V4 Pro 0423 38.7 from 5 benchmarks, GPT-5.4 64.4 from 3 benchmarks.
Widest category
Math, 22.6 points apart on average over 6 shared benchmarks.
Widest single gap
FrontierMath, tier 4: DeepSeek V4 Pro 0423 2.4% against GPT-5.4 49.0%, 46.6 points apart on a 0 to 100 scale.
Output price
DeepSeek V4 Pro 0423 $2.976 against GPT-5.4 $15.00 per million output tokens, 5.0x apart.
Context window
DeepSeek V4 Pro 0423 takes 1.05M 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 V4 Pro 0423BarsGPT-5.4Ties
Coding113
Intelligence02
Agentic work04
Reasoning08
Math06
Knowledge29
Web design62
General219
All shared boards1163
CodingLike-for-likeSix of these boards feed the Vibe Coding Index113
Coding benchmarks for DeepSeek V4 Pro 0423 and GPT-5.4
BenchmarkDeepSeek V4 Pro 0423GPT-5.4Leader
LMArena WebDev14471464GPT-5.4
AA Coding Index59.471.1GPT-5.4
LiveCodeBench (Vals AI)87.5%84.1%DeepSeek V4 Pro 0423
SWE-bench Verified (Vals AI)77.4%78.2%GPT-5.4
Terminal-Bench 4 (Vals AI)11.1%Not measuredOnly DeepSeek V4 Pro 0423 measured
Vibe Code Bench (Vals AI)49.9%67.4%GPT-5.4
Code migration (Vals AI)26.2%35.0%GPT-5.4
ProgramBench (Vals AI)0.0%0.5%GPT-5.4
Terminal-Bench 2.1 (Vals AI)50.2%Not measuredOnly DeepSeek V4 Pro 0423 measured
SkillsBench (Vals AI)51.3%51.7%GPT-5.4
Terminal-Bench Hard (Artificial Analysis run)Not measured57.6%Only GPT-5.4 measured
Terminal-BenchNot measured81.8%Only GPT-5.4 measured
FrontierCode17.6%Not measuredOnly DeepSeek V4 Pro 0423 measured
GSO-BenchNot measured31.4%Only GPT-5.4 measured
WeirdML48.9%77.7%GPT-5.4
MirrorCodeNot measured15.6%Only GPT-5.4 measured
ALE-Bench1006.11607.0GPT-5.4
LMArena Text: coding14701496GPT-5.4
LMArena Text: software and IT14691491GPT-5.4
LMArena WebDev: React14411454GPT-5.4
LMArena WebDev: HTML14351478GPT-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 V4 Pro 0423 and GPT-5.4
BenchmarkDeepSeek V4 Pro 0423GPT-5.4Leader
AA Intelligence Index30.439.0GPT-5.4
Epoch Capabilities Index149.1157.3GPT-5.4
Agentic workLike-for-likePublic boards, shown as published, kept out of the index04
Agentic work benchmarks for DeepSeek V4 Pro 0423 and GPT-5.4
BenchmarkDeepSeek V4 Pro 0423GPT-5.4Leader
AA Agentic Index26.3Not measuredOnly DeepSeek V4 Pro 0423 measured
Design Arena: agents building web apps10001059GPT-5.4
Design Arena: agents building full-stack apps9481017GPT-5.4
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 games10591135GPT-5.4
Finance Agent (Vals AI)44.1%Not measuredOnly DeepSeek V4 Pro 0423 measured
Tax Agent Bench (Vals AI)25.2%Not measuredOnly DeepSeek V4 Pro 0423 measured
Legal Research Bench (Vals AI)23.1%Not measuredOnly DeepSeek V4 Pro 0423 measured
Excel Modeling Benchmark (Vals AI)51.6%Not measuredOnly DeepSeek V4 Pro 0423 measured
τ²-Bench TelecomNot measured87.1%Only GPT-5.4 measured
APEX-AgentsNot measured52.4%Only GPT-5.4 measured
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$3,285$6,144GPT-5.4
Neither model has a result on the other 25 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index08
Reasoning benchmarks for DeepSeek V4 Pro 0423 and GPT-5.4
BenchmarkDeepSeek V4 Pro 0423GPT-5.4Leader
GPQA Diamond89.4%91.7%GPT-5.4
MMMU Pro (Vals AI)Not measured87.5%Only GPT-5.4 measured
GPQA Diamond (Artificial Analysis run)Not measured92.0%Only GPT-5.4 measured
Humanity's Last Exam (Artificial Analysis run)Not measured43.7%Only GPT-5.4 measured
GPQA Diamond (Epoch AI run)90.9%93.3%GPT-5.4
ARC-AGINot measured93.7%Only GPT-5.4 measured
ARC-AGI-2Not measured74.0%Only GPT-5.4 measured
Chess puzzles19.0%48.0%GPT-5.4
Mystery game puzzles17.0%37.0%GPT-5.4
EBR-benchNot measured25.4%Only GPT-5.4 measured
LMArena Text: hard prompts14611485GPT-5.4
LMArena Text: expert14631507GPT-5.4
LMArena Text: hard prompts in English14661479GPT-5.4
LMArena Vision: diagramsNot measured1327Only GPT-5.4 measured
LMArena Vision: homeworkNot measured1336Only GPT-5.4 measured
Kagi LLM Benchmark53.5%63.8%GPT-5.4
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index06
Math benchmarks for DeepSeek V4 Pro 0423 and GPT-5.4
BenchmarkDeepSeek V4 Pro 0423GPT-5.4Leader
AIMENot measured96.7%Only GPT-5.4 measured
OTIS Mock AIME96.7%97.8%GPT-5.4
FrontierMath, tiers 1 to 345.3%78.6%GPT-5.4
FrontierMath, tier 42.4%49.0%GPT-5.4
ProofBench16.0%56.0%GPT-5.4
LMArena Text: math14431488GPT-5.4
LMArena Text: mathematical work14551497GPT-5.4
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index29
Knowledge benchmarks for DeepSeek V4 Pro 0423 and GPT-5.4
BenchmarkDeepSeek V4 Pro 0423GPT-5.4Leader
MMLU Pro87.3%87.5%GPT-5.4
LegalBench (Vals AI)80.3%86.0%GPT-5.4
CaseLaw (Vals AI)59.4%63.8%GPT-5.4
CorpFin (Vals AI)61.4%65.3%GPT-5.4
TaxEval (Vals AI)72.1%74.0%GPT-5.4
MortgageTax (Vals AI)Not measured68.3%Only GPT-5.4 measured
MedQA (Vals AI)Not measured96.1%Only GPT-5.4 measured
MedCode (Vals AI)40.5%41.3%GPT-5.4
SimpleQA Verified47.0%45.1%DeepSeek V4 Pro 0423
LMArena Text: science14701479GPT-5.4
LMArena Text: medicine and healthcare14661458DeepSeek V4 Pro 0423
LMArena Text: legal and government14641486GPT-5.4
LMArena Text: business and finance14431474GPT-5.4
Neither model has a result on the other 5 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index62
Web design benchmarks for DeepSeek V4 Pro 0423 and GPT-5.4
BenchmarkDeepSeek V4 Pro 0423GPT-5.4Leader
Design Arena: websites12341198DeepSeek V4 Pro 0423
Design Arena: UI components12191212DeepSeek V4 Pro 0423
Design Arena: game dev12281194DeepSeek V4 Pro 0423
Design Arena: data viz12031196DeepSeek V4 Pro 0423
Design Arena: 3D12531065DeepSeek V4 Pro 0423
Design Arena: all code categories12401179DeepSeek V4 Pro 0423
Design Arena: SVG11391141GPT-5.4
Design Arena: ASCII art11491188GPT-5.4
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index219
General benchmarks for DeepSeek V4 Pro 0423 and GPT-5.4
BenchmarkDeepSeek V4 Pro 0423GPT-5.4Leader
Public Benefits Bench (Vals AI)62.9%Not measuredOnly DeepSeek V4 Pro 0423 measured
SAGE (Vals AI)Not measured43.3%Only GPT-5.4 measured
MedScribe (Vals AI)75.1%77.5%GPT-5.4
IFBenchNot measured73.9%Only GPT-5.4 measured
Long context reasoning (AA-LCR)Not measured82.0%Only GPT-5.4 measured
DTBench90.7%94.4%GPT-5.4
LMCA41.2%52.0%GPT-5.4
CL-benchNot measured27.9%Only GPT-5.4 measured
Surface Evolver Bench40.0%Not measuredOnly DeepSeek V4 Pro 0423 measured
Furniture assemblyNot measured37.5%Only GPT-5.4 measured
CL-bench Life13.5%21.7%GPT-5.4
LMArena Text14511469GPT-5.4
LMArena Text: instruction following14451469GPT-5.4
LMArena Text: creative writing14461439DeepSeek V4 Pro 0423
LMArena VisionNot measured1303Only GPT-5.4 measured
LMArena Text: English14591467GPT-5.4
LMArena Text: non-English14391465GPT-5.4
LMArena Text: Chinese14811520GPT-5.4
LMArena Text: German14581472GPT-5.4
LMArena Text: Japanese14461485GPT-5.4
LMArena Text: Korean14091449GPT-5.4
LMArena Text: French14731493GPT-5.4
LMArena Text: Spanish14571452DeepSeek V4 Pro 0423
LMArena Text: Russian14531480GPT-5.4
LMArena Text: Polish14611472GPT-5.4
LMArena Text: multi-turn14681482GPT-5.4
LMArena Text: longer queries14581473GPT-5.4
LMArena Text: writing and language14471458GPT-5.4
LMArena Text: entertainment and media14311438GPT-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 10 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for DeepSeek V4 Pro 0423 and GPT-5.4
BenchmarkDeepSeek V4 Pro 0423GPT-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 V4 Pro 0423$0.0028Fits in one request
GPT-5.4$0.010Fits in one request

DeepSeek V4 Pro 0423 costs less

Repository review

50K input + 3K output tokens

DeepSeek V4 Pro 0423$0.077Fits in one request
GPT-5.4$0.170Fits in one request

DeepSeek V4 Pro 0423 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V4 Pro 0423$0.301Fits in one request
GPT-5.4$0.650Fits in one request

DeepSeek V4 Pro 0423 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 V4 Pro 0423 and GPT-5.4
SpecificationDeepSeek V4 Pro 0423OpenAI GPT-5.4
MakerDeepSeekOpenAI
WeightsOpen weightsNo public weights listed
ReleasedApril 24, 2026March 5, 2026
Context window1.05M1.05M
Input $/Mtok$1.358$2.50
Output $/Mtok$2.976$15.00
Coding index38.764.4
Independent measurements behind it53
Cost per solved task$0.57$1.02
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V4 Pro 0423 better than GPT-5.4 for coding?

Pick GPT-5.4 for coding: it scores 64.4 on the Vibe Coding Index against 38.7 for DeepSeek V4 Pro 0423, though on 3 benchmarks against 5. Pick DeepSeek V4 Pro 0423 for output tokens 5.0x cheaper ($2.976 vs $15.00 per million) and a lower cost per solved task ($0.57 against $1.02).

Which is cheaper, DeepSeek V4 Pro 0423 or GPT-5.4?

DeepSeek V4 Pro 0423 costs $1.358 per million input tokens and $2.976 per million output tokens; GPT-5.4 costs $2.50 and $15.00. Per solved SWE-bench Verified task, DeepSeek V4 Pro 0423 costs $0.57 and GPT-5.4 $1.02.

Which has the bigger context window, DeepSeek V4 Pro 0423 or GPT-5.4?

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

How many benchmarks is the DeepSeek V4 Pro 0423 vs GPT-5.4 comparison based on?

74 benchmarks have a result for both models as of October 22, 2026. DeepSeek V4 Pro 0423's coding index rests on 5 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-v4-pro-vs-gpt-5-4" title="DeepSeek V4 Pro 0423 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-v4-pro-vs-gpt-5-4">LLMBenchmark.ai, DeepSeek V4 Pro 0423 vs GPT-5.4</a></p>