Enter opens the highlighted result. Esc closes.

DeepSeek V3 0324 vs GPT-4

DeepSeek V3 0324 leads GPT-4 on the Artificial Analysis Intelligence Index, 9.7 to 6.7, and DeepSeek V3 0324 costs 56.1x less per output token ($1.07 vs $60.00 per million). Updated October 22, 2026; 8 benchmarks have a result for both.

Replace DeepSeek V3 0324 Replace GPT-4
DeepSeek V3 0324DeepSeek
Coding
No data
Overall
No data
Output $/M
$1.07
7
GPT-4OpenAI
Coding
No data
Overall
No data
Output $/M
$60.00
1
vs boards won of 8 shared

DeepSeek V3 0324 or GPT-4: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick DeepSeek V3 0324 for output tokens 56.1x cheaper ($1.07 vs $60.00 per million) and a larger context window (164K against 8K tokens).

Model ADeepSeek V3 0324DeepSeekNot benchmarkedNo coding benchmarkNo cost per solved taskModel BGPT-4OpenAINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
8
DeepSeek V3 0324 only
27
GPT-4 only
37
Like-for-like categories
5 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 0324 not benchmarked, GPT-4 not benchmarked.
Widest category
Reasoning, 30.6 points apart on average over 1 shared benchmark.
Widest single gap
GPQA Diamond (Artificial Analysis run): DeepSeek V3 0324 65.5% against GPT-4 34.9%, 30.6 points apart on a 0 to 100 scale.
Output price
DeepSeek V3 0324 $1.07 against GPT-4 $60.00 per million output tokens, 56.1x apart.
Context window
DeepSeek V3 0324 takes 164K tokens, GPT-4 8K.

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 0324BarsGPT-4Ties
Coding20
Intelligence10
Reasoning10
Knowledge10
General21
All shared boards71
CodingLike-for-likeSix of these boards feed the Vibe Coding Index20
Coding benchmarks for DeepSeek V3 0324 and GPT-4
BenchmarkDeepSeek V3 0324GPT-4Leader
SWE-bench Verified42.0%22.4%DeepSeek V3 0324
SWE-bench LiteNot measured39.7%Only GPT-4 measured
SWE-bench (full test set)Not measured12.5%Only GPT-4 measured
AA Coding Index21.213.1DeepSeek V3 0324
LiveCodeBench (Vals AI)65.5%Not measuredOnly DeepSeek V3 0324 measured
LiveCodeBench (Artificial Analysis run)40.5%Not measuredOnly DeepSeek V3 0324 measured
SciCode39.0%Not measuredOnly DeepSeek V3 0324 measured
Terminal-Bench Hard (Artificial Analysis run)15.2%Not measuredOnly DeepSeek V3 0324 measured
WeirdML36.1%Not measuredOnly DeepSeek V3 0324 measured
LMArena Text: codingNot measured1209Only GPT-4 measured
LMArena Text: software and ITNot measured1195Only GPT-4 measured
Neither model has a result on the other 28 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for DeepSeek V3 0324 and GPT-4
BenchmarkDeepSeek V3 0324GPT-4Leader
AA Intelligence Index9.76.7DeepSeek V3 0324
Epoch Capabilities IndexNot measured125.7Only GPT-4 measured
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
Agentic work benchmarks for DeepSeek V3 0324 and GPT-4
BenchmarkDeepSeek V3 0324GPT-4Leader
AA Agentic Index0.8Not measuredOnly DeepSeek V3 0324 measured
τ²-Bench Telecom47.1%Not measuredOnly DeepSeek V3 0324 measured
METR time horizons49.6%Not measuredOnly DeepSeek V3 0324 measured
Neither model has a result on the other 38 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index10
Reasoning benchmarks for DeepSeek V3 0324 and GPT-4
BenchmarkDeepSeek V3 0324GPT-4Leader
GPQA Diamond61.6%Not measuredOnly DeepSeek V3 0324 measured
GPQA Diamond (Artificial Analysis run)65.5%34.9%DeepSeek V3 0324
Humanity's Last Exam (Artificial Analysis run)4.7%Not measuredOnly DeepSeek V3 0324 measured
GPQA Diamond (Epoch AI run)67.6%Not measuredOnly DeepSeek V3 0324 measured
SimpleBench27.2%Not measuredOnly DeepSeek V3 0324 measured
BIG-Bench HardNot measured75.1%Only GPT-4 measured
LMArena Text: hard promptsNot measured1200Only GPT-4 measured
LMArena Text: expertNot measured1149Only GPT-4 measured
LMArena Text: hard prompts in EnglishNot measured1209Only GPT-4 measured
Neither model has a result on the other 13 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index10 boards, none shared
Math benchmarks for DeepSeek V3 0324 and GPT-4
BenchmarkDeepSeek V3 0324GPT-4Leader
AIME52.2%Not measuredOnly DeepSeek V3 0324 measured
MATH 500 (Vals AI)88.6%Not measuredOnly DeepSeek V3 0324 measured
MGSM (Vals AI)91.7%Not measuredOnly DeepSeek V3 0324 measured
AA Math Index41.0Not measuredOnly DeepSeek V3 0324 measured
AIME 2025 (Artificial Analysis run)41.0%Not measuredOnly DeepSeek V3 0324 measured
OTIS Mock AIME37.8%Not measuredOnly DeepSeek V3 0324 measured
MATH level 575.5%Not measuredOnly DeepSeek V3 0324 measured
GSM8KNot measured92.0%Only GPT-4 measured
LMArena Text: mathNot measured1230Only GPT-4 measured
LMArena Text: mathematical workNot measured1228Only GPT-4 measured
Neither model has a result on the other 3 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index10
Knowledge benchmarks for DeepSeek V3 0324 and GPT-4
BenchmarkDeepSeek V3 0324GPT-4Leader
MMLU Pro79.5%Not measuredOnly DeepSeek V3 0324 measured
LegalBench (Vals AI)77.7%Not measuredOnly DeepSeek V3 0324 measured
CorpFin (Vals AI)54.7%Not measuredOnly DeepSeek V3 0324 measured
TaxEval (Vals AI)71.1%Not measuredOnly DeepSeek V3 0324 measured
MedQA (Vals AI)82.0%Not measuredOnly DeepSeek V3 0324 measured
MMLU Pro (Artificial Analysis run)81.9%56.2%DeepSeek V3 0324
MMLUNot measured86.4%Only GPT-4 measured
AI2 Reasoning ChallengeNot measured96.3%Only GPT-4 measured
LMArena Text: scienceNot measured1177Only GPT-4 measured
LMArena Text: medicine and healthcareNot measured1145Only GPT-4 measured
LMArena Text: legal and governmentNot measured1191Only GPT-4 measured
LMArena Text: business and financeNot measured1145Only GPT-4 measured
Neither model has a result on the other 6 boards here
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Web design benchmarks for DeepSeek V3 0324 and GPT-4
BenchmarkDeepSeek V3 0324GPT-4Leader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index21
General benchmarks for DeepSeek V3 0324 and GPT-4
BenchmarkDeepSeek V3 0324GPT-4Leader
IFBench41.0%33.2%DeepSeek V3 0324
Long context reasoning (AA-LCR)40.7%Not measuredOnly DeepSeek V3 0324 measured
DTBench64.8%62.7%DeepSeek V3 0324
LMCA15.5%17.1%GPT-4
Fiction.LiveBench50.0%Not measuredOnly DeepSeek V3 0324 measured
Creative writing (Lech Mazur)77.0%Not measuredOnly DeepSeek V3 0324 measured
HellaSwagNot measured95.3%Only GPT-4 measured
WinoGrandeNot measured87.5%Only GPT-4 measured
LMArena TextNot measured1206Only GPT-4 measured
LMArena Text: instruction followingNot measured1201Only GPT-4 measured
LMArena Text: creative writingNot measured1191Only GPT-4 measured
LMArena Text: EnglishNot measured1220Only GPT-4 measured
LMArena Text: non-EnglishNot measured1194Only GPT-4 measured
LMArena Text: ChineseNot measured1184Only GPT-4 measured
LMArena Text: GermanNot measured1198Only GPT-4 measured
LMArena Text: JapaneseNot measured1137Only GPT-4 measured
LMArena Text: KoreanNot measured1087Only GPT-4 measured
LMArena Text: FrenchNot measured1220Only GPT-4 measured
LMArena Text: SpanishNot measured1197Only GPT-4 measured
LMArena Text: RussianNot measured1195Only GPT-4 measured
LMArena Text: PolishNot measured1265Only GPT-4 measured
LMArena Text: multi-turnNot measured1206Only GPT-4 measured
LMArena Text: longer queriesNot measured1190Only GPT-4 measured
LMArena Text: writing and languageNot measured1219Only GPT-4 measured
LMArena Text: entertainment and mediaNot measured1184Only GPT-4 measured
Neither model has a result on the other 21 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for DeepSeek V3 0324 and GPT-4
BenchmarkDeepSeek V3 0324GPT-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 0324$0.0008Fits in one request
GPT-4$0.060Fits in one request

DeepSeek V3 0324 costs less

Repository review

50K input + 3K output tokens

DeepSeek V3 0324$0.017Fits in one request
GPT-4$1.68Exceeds the context window

DeepSeek V3 0324 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V3 0324$0.065Exceeds the context window
GPT-4$6.60Exceeds the context window

DeepSeek V3 0324 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 0324 and GPT-4
SpecificationDeepSeek V3 0324OpenAI GPT-4
MakerDeepSeekOpenAI
WeightsOpen weightsNo public weights listed
ReleasedMarch 24, 2025May 28, 2023
Context window164K8K
Input $/Mtok$0.27$30.00
Output $/Mtok$1.07$60.00
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V3 0324 better than GPT-4 for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick DeepSeek V3 0324 for output tokens 56.1x cheaper ($1.07 vs $60.00 per million) and a larger context window (164K against 8K tokens).

Which is cheaper, DeepSeek V3 0324 or GPT-4?

DeepSeek V3 0324 costs $0.27 per million input tokens and $1.07 per million output tokens; GPT-4 costs $30.00 and $60.00. Cost per solved task is known for neither of them.

Which has the bigger context window, DeepSeek V3 0324 or GPT-4?

DeepSeek V3 0324, with 164K tokens against 8K.

How many benchmarks is the DeepSeek V3 0324 vs GPT-4 comparison based on?

8 benchmarks have a result for both models as of October 22, 2026. DeepSeek V3 0324's coding index rests on 0 independent benchmarks and GPT-4's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next