Enter opens the highlighted result. Esc closes.

DeepSeek V4 Pro 0423 vs GPT-5.4 Mini

DeepSeek V4 Pro 0423 leads GPT-5.4 Mini on coding, 38.7 to 35.8 on the Vibe Coding Index, and DeepSeek V4 Pro 0423 costs 1.5x less per output token ($2.976 vs $4.50 per million). Updated October 22, 2026; 65 benchmarks have a result for both.

Replace DeepSeek V4 Pro 0423 Replace GPT-5.4 Mini
DeepSeek V4 Pro 0423DeepSeek
Coding
38.7
Overall
50.0
Output $/M
$2.976
55
GPT-5.4 MiniOpenAI
Coding
35.8
Overall
44.0
Output $/M
$4.50
9
vs boards won of 65 shared, 1 tied

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

Pick DeepSeek V4 Pro 0423 for coding: it scores 38.7 on the Vibe Coding Index against 35.8 for GPT-5.4 Mini.

Pick GPT-5.4 Mini for work measured by Terminal-Bench 2.1 (Vals AI) or FrontierCode, where it leads.

Model ADeepSeek V4 Pro 0423DeepSeek38.7/1005 independent benchmarks$0.57 per solved taskModel BGPT-5.4 MiniOpenAI35.8/1005 independent benchmarks$0.70 per solved task
Shared results
65
DeepSeek V4 Pro 0423 only
19
GPT-5.4 Mini only
24
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 V4 Pro 0423 38.7 from 5 benchmarks, GPT-5.4 Mini 35.8 from 5 benchmarks.
Widest category
Agentic work, 8.6 points apart on average over 5 shared benchmarks.
Widest single gap
SimpleQA Verified: DeepSeek V4 Pro 0423 47.0% against GPT-5.4 Mini 29.4%, 17.6 points apart on a 0 to 100 scale.
Output price
DeepSeek V4 Pro 0423 $2.976 against GPT-5.4 Mini $4.50 per million output tokens, 1.5x apart.
Context window
DeepSeek V4 Pro 0423 takes 1.05M 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 V4 Pro 0423BarsGPT-5.4 MiniTies
Coding1141 tie
Intelligence20
Agentic work41
Reasoning71
Math33
Knowledge90
General190
All shared boards5591 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index114
Coding benchmarks for DeepSeek V4 Pro 0423 and GPT-5.4 Mini
BenchmarkDeepSeek V4 Pro 0423GPT-5.4 MiniLeader
LMArena WebDev14471397DeepSeek V4 Pro 0423
AA Coding Index59.456.1DeepSeek V4 Pro 0423
LiveCodeBench (Vals AI)87.5%81.5%DeepSeek V4 Pro 0423
SWE-bench Verified (Vals AI)77.4%73.0%DeepSeek V4 Pro 0423
Terminal-Bench 4 (Vals AI)11.1%2.5%DeepSeek V4 Pro 0423
Vibe Code Bench (Vals AI)49.9%48.0%DeepSeek V4 Pro 0423
Code migration (Vals AI)26.2%12.9%DeepSeek V4 Pro 0423
ProgramBench (Vals AI)0.0%0.0%Tie
Terminal-Bench 2.1 (Vals AI)50.2%54.7%GPT-5.4 Mini
SkillsBench (Vals AI)51.3%Not measuredOnly DeepSeek V4 Pro 0423 measured
SciCodeNot measured52.1%Only GPT-5.4 Mini measured
Terminal-Bench Hard (Artificial Analysis run)Not measured52.3%Only GPT-5.4 Mini measured
FrontierCode17.6%27.0%GPT-5.4 Mini
WeirdML48.9%60.3%GPT-5.4 Mini
ALE-Bench1006.11188.6GPT-5.4 Mini
LMArena Text: coding14701438DeepSeek V4 Pro 0423
LMArena Text: software and IT14691436DeepSeek V4 Pro 0423
LMArena WebDev: React14411386DeepSeek V4 Pro 0423
LMArena WebDev: HTML14351419DeepSeek V4 Pro 0423
Neither model has a result on the other 20 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for DeepSeek V4 Pro 0423 and GPT-5.4 Mini
BenchmarkDeepSeek V4 Pro 0423GPT-5.4 MiniLeader
AA Intelligence Index30.424.1DeepSeek V4 Pro 0423
Epoch Capabilities Index149.1148.7DeepSeek V4 Pro 0423
Agentic workLike-for-likePublic boards, shown as published, kept out of the index41
Agentic work benchmarks for DeepSeek V4 Pro 0423 and GPT-5.4 Mini
BenchmarkDeepSeek V4 Pro 0423GPT-5.4 MiniLeader
AA Agentic Index26.317.9DeepSeek V4 Pro 0423
Design Arena: agents building web apps1000Not measuredOnly DeepSeek V4 Pro 0423 measured
Design Arena: agents building full-stack apps948Not measuredOnly DeepSeek V4 Pro 0423 measured
Design Arena: agents building Godot games1059Not measuredOnly DeepSeek V4 Pro 0423 measured
Finance Agent (Vals AI)44.1%45.4%GPT-5.4 Mini
Tax Agent Bench (Vals AI)25.2%8.8%DeepSeek V4 Pro 0423
Legal Research Bench (Vals AI)23.1%12.5%DeepSeek V4 Pro 0423
Excel Modeling Benchmark (Vals AI)51.6%45.4%DeepSeek V4 Pro 0423
τ²-Bench TelecomNot measured83.3%Only GPT-5.4 Mini measured
DeepResearch BenchNot measured36.3%Only GPT-5.4 Mini measured
Vending-Bench 2$3,285Not measuredOnly DeepSeek V4 Pro 0423 measured
Neither model has a result on the other 30 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index71
Reasoning benchmarks for DeepSeek V4 Pro 0423 and GPT-5.4 Mini
BenchmarkDeepSeek V4 Pro 0423GPT-5.4 MiniLeader
GPQA Diamond89.4%83.1%DeepSeek V4 Pro 0423
MMMU Pro (Vals AI)Not measured79.3%Only GPT-5.4 Mini measured
GPQA Diamond (Artificial Analysis run)Not measured87.5%Only GPT-5.4 Mini measured
Humanity's Last Exam (Artificial Analysis run)Not measured28.1%Only GPT-5.4 Mini measured
GPQA Diamond (Epoch AI run)90.9%86.9%DeepSeek V4 Pro 0423
ARC-AGINot measured63.7%Only GPT-5.4 Mini measured
ARC-AGI-2Not measured18.9%Only GPT-5.4 Mini measured
Chess puzzles19.0%23.0%GPT-5.4 Mini
Mystery game puzzles17.0%11.0%DeepSeek V4 Pro 0423
LMArena Text: hard prompts14611424DeepSeek V4 Pro 0423
LMArena Text: expert14631435DeepSeek V4 Pro 0423
LMArena Text: hard prompts in English14661420DeepSeek V4 Pro 0423
LMArena Vision: diagramsNot measured1266Only GPT-5.4 Mini measured
LMArena Vision: homeworkNot measured1285Only GPT-5.4 Mini measured
Kagi LLM Benchmark53.5%37.9%DeepSeek V4 Pro 0423
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index33
Math benchmarks for DeepSeek V4 Pro 0423 and GPT-5.4 Mini
BenchmarkDeepSeek V4 Pro 0423GPT-5.4 MiniLeader
AIMENot measured95.6%Only GPT-5.4 Mini measured
OTIS Mock AIME96.7%88.9%DeepSeek V4 Pro 0423
FrontierMath, tiers 1 to 345.3%51.2%GPT-5.4 Mini
FrontierMath, tier 42.4%9.8%GPT-5.4 Mini
ProofBench16.0%21.0%GPT-5.4 Mini
LMArena Text: math14431418DeepSeek V4 Pro 0423
LMArena Text: mathematical work14551429DeepSeek V4 Pro 0423
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index90
Knowledge benchmarks for DeepSeek V4 Pro 0423 and GPT-5.4 Mini
BenchmarkDeepSeek V4 Pro 0423GPT-5.4 MiniLeader
MMLU Pro87.3%84.5%DeepSeek V4 Pro 0423
LegalBench (Vals AI)80.3%Not measuredOnly DeepSeek V4 Pro 0423 measured
CaseLaw (Vals AI)59.4%51.7%DeepSeek V4 Pro 0423
CorpFin (Vals AI)61.4%60.9%DeepSeek V4 Pro 0423
TaxEval (Vals AI)72.1%71.2%DeepSeek V4 Pro 0423
MortgageTax (Vals AI)Not measured63.5%Only GPT-5.4 Mini measured
MedCode (Vals AI)40.5%Not measuredOnly DeepSeek V4 Pro 0423 measured
SimpleQA Verified47.0%29.4%DeepSeek V4 Pro 0423
LMArena Text: science14701417DeepSeek V4 Pro 0423
LMArena Text: medicine and healthcare14661395DeepSeek V4 Pro 0423
LMArena Text: legal and government14641414DeepSeek V4 Pro 0423
LMArena Text: business and finance14431418DeepSeek V4 Pro 0423
Neither model has a result on the other 6 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for DeepSeek V4 Pro 0423 and GPT-5.4 Mini
BenchmarkDeepSeek V4 Pro 0423GPT-5.4 MiniLeader
Design Arena: websites1234Not measuredOnly DeepSeek V4 Pro 0423 measured
Design Arena: UI components1219Not measuredOnly DeepSeek V4 Pro 0423 measured
Design Arena: game dev1228Not measuredOnly DeepSeek V4 Pro 0423 measured
Design Arena: data viz1203Not measuredOnly DeepSeek V4 Pro 0423 measured
Design Arena: 3D1253Not measuredOnly DeepSeek V4 Pro 0423 measured
Design Arena: all code categories1240Not measuredOnly DeepSeek V4 Pro 0423 measured
Design Arena: SVG1139Not measuredOnly DeepSeek V4 Pro 0423 measured
Design Arena: ASCII art1149Not measuredOnly DeepSeek V4 Pro 0423 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index190
General benchmarks for DeepSeek V4 Pro 0423 and GPT-5.4 Mini
BenchmarkDeepSeek V4 Pro 0423GPT-5.4 MiniLeader
Public Benefits Bench (Vals AI)62.9%Not measuredOnly DeepSeek V4 Pro 0423 measured
SAGE (Vals AI)Not measured50.8%Only GPT-5.4 Mini measured
MedScribe (Vals AI)75.1%Not measuredOnly DeepSeek V4 Pro 0423 measured
Vals Multimodal IndexNot measured54.2%Only GPT-5.4 Mini measured
IFBenchNot measured73.3%Only GPT-5.4 Mini measured
Long context reasoning (AA-LCR)Not measured77.0%Only GPT-5.4 Mini measured
DTBench90.7%80.0%DeepSeek V4 Pro 0423
LMCA41.2%40.8%DeepSeek V4 Pro 0423
Surface Evolver Bench40.0%Not measuredOnly DeepSeek V4 Pro 0423 measured
CL-bench Life13.5%Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text14511412DeepSeek V4 Pro 0423
LMArena Text: instruction following14451405DeepSeek V4 Pro 0423
LMArena Text: creative writing14461370DeepSeek V4 Pro 0423
LMArena VisionNot measured1245Only GPT-5.4 Mini measured
LMArena Text: English14591412DeepSeek V4 Pro 0423
LMArena Text: non-English14391405DeepSeek V4 Pro 0423
LMArena Text: Chinese14811446DeepSeek V4 Pro 0423
LMArena Text: German14581408DeepSeek V4 Pro 0423
LMArena Text: Japanese14461375DeepSeek V4 Pro 0423
LMArena Text: Korean14091370DeepSeek V4 Pro 0423
LMArena Text: French14731441DeepSeek V4 Pro 0423
LMArena Text: Spanish14571405DeepSeek V4 Pro 0423
LMArena Text: Russian14531417DeepSeek V4 Pro 0423
LMArena Text: Polish14611415DeepSeek V4 Pro 0423
LMArena Text: multi-turn14681429DeepSeek V4 Pro 0423
LMArena Text: longer queries14581408DeepSeek V4 Pro 0423
LMArena Text: writing and language14471393DeepSeek V4 Pro 0423
LMArena Text: entertainment and media14311373DeepSeek V4 Pro 0423
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 12 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 Mini
BenchmarkDeepSeek V4 Pro 0423GPT-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 V4 Pro 0423$0.0028Fits in one request
GPT-5.4 Mini$0.0030Fits 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 Mini$0.051Fits in one request

GPT-5.4 Mini costs less

Agent loop

200K input + 10K output tokens

DeepSeek V4 Pro 0423$0.301Fits in one request
GPT-5.4 Mini$0.195Fits in one request

GPT-5.4 Mini 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 Mini
SpecificationDeepSeek V4 Pro 0423OpenAI GPT-5.4 Mini
MakerDeepSeekOpenAI
WeightsOpen weightsNo public weights listed
ReleasedApril 24, 2026March 17, 2026
Context window1.05M400K
Input $/Mtok$1.358$0.75
Output $/Mtok$2.976$4.50
Coding index38.735.8
Independent measurements behind it55
Cost per solved task$0.57$0.70
SourceOpenRouter listingOpenRouter listing

Questions

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

Pick DeepSeek V4 Pro 0423 for coding: it scores 38.7 on the Vibe Coding Index against 35.8 for GPT-5.4 Mini. Pick GPT-5.4 Mini for work measured by Terminal-Bench 2.1 (Vals AI) or FrontierCode, where it leads.

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

DeepSeek V4 Pro 0423 costs $1.358 per million input tokens and $2.976 per million output tokens; GPT-5.4 Mini costs $0.75 and $4.50. Per solved SWE-bench Verified task, DeepSeek V4 Pro 0423 costs $0.57 and GPT-5.4 Mini $0.70.

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

DeepSeek V4 Pro 0423, with 1.05M tokens against 400K.

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

65 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 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-v4-pro-vs-gpt-5-4-mini" title="DeepSeek V4 Pro 0423 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-v4-pro-vs-gpt-5-4-mini">LLMBenchmark.ai, DeepSeek V4 Pro 0423 vs GPT-5.4 Mini</a></p>