Enter opens the highlighted result. Esc closes.

DeepSeek V4 Flash 0423 vs GPT-4

DeepSeek V4 Flash 0423 leads GPT-4 on the Artificial Analysis Intelligence Index, 24.4 to 6.7, and DeepSeek V4 Flash 0423 costs 214.3x less per output token ($0.28 vs $60.00 per million). Updated October 22, 2026; 33 benchmarks have a result for both.

Replace DeepSeek V4 Flash 0423 Replace GPT-4
DeepSeek V4 Flash 0423DeepSeek
Coding
No data
Overall
No data
Output $/M
$0.28
33
GPT-4OpenAI
Coding
No data
Overall
No data
Output $/M
$60.00
0
vs boards won of 33 shared

DeepSeek V4 Flash 0423 or GPT-4: which to pick

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

Pick DeepSeek V4 Flash 0423 for output tokens 214.3x cheaper ($0.28 vs $60.00 per million) and a larger context window (1.05M against 8K tokens).

Model ADeepSeek V4 Flash 0423DeepSeekNot benchmarked1 independent benchmarkNo cost per solved taskModel BGPT-4OpenAINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
33
DeepSeek V4 Flash 0423 only
16
GPT-4 only
12
Like-for-like categories
6 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 Flash 0423 not benchmarked, GPT-4 not benchmarked.
Widest category
Knowledge, 45.8 points apart on average over 4 shared benchmarks.
Widest single gap
LMArena Text: medicine and healthcare: DeepSeek V4 Flash 0423 1448 against GPT-4 1145, 50.5 points apart on a 0 to 100 scale.
Output price
DeepSeek V4 Flash 0423 $0.28 against GPT-4 $60.00 per million output tokens, 214.3x apart.
Context window
DeepSeek V4 Flash 0423 takes 1.05M 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 V4 Flash 0423BarsGPT-4Ties
Coding30
Intelligence20
Reasoning30
Math20
Knowledge40
General190
All shared boards330
CodingLike-for-likeSix of these boards feed the Vibe Coding Index30
Coding benchmarks for DeepSeek V4 Flash 0423 and GPT-4
BenchmarkDeepSeek V4 Flash 0423GPT-4Leader
SWE-bench VerifiedNot measured22.4%Only GPT-4 measured
SWE-bench LiteNot measured39.7%Only GPT-4 measured
SWE-bench (full test set)Not measured12.5%Only GPT-4 measured
LMArena WebDev1582Not measuredOnly DeepSeek V4 Flash 0423 measured
AA Coding Index52.013.1DeepSeek V4 Flash 0423
WeirdML45.6%Not measuredOnly DeepSeek V4 Flash 0423 measured
ALE-Bench678.2Not measuredOnly DeepSeek V4 Flash 0423 measured
LMArena Text: coding14571209DeepSeek V4 Flash 0423
LMArena Text: software and IT14531195DeepSeek V4 Flash 0423
LMArena WebDev: React1585Not measuredOnly DeepSeek V4 Flash 0423 measured
LMArena WebDev: HTML1558Not measuredOnly DeepSeek V4 Flash 0423 measured
Neither model has a result on the other 28 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for DeepSeek V4 Flash 0423 and GPT-4
BenchmarkDeepSeek V4 Flash 0423GPT-4Leader
AA Intelligence Index24.46.7DeepSeek V4 Flash 0423
Epoch Capabilities Index146.1125.7DeepSeek V4 Flash 0423
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
Agentic work benchmarks for DeepSeek V4 Flash 0423 and GPT-4
BenchmarkDeepSeek V4 Flash 0423GPT-4Leader
AA Agentic Index26.3Not measuredOnly DeepSeek V4 Flash 0423 measured
Neither model has a result on the other 40 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index30
Reasoning benchmarks for DeepSeek V4 Flash 0423 and GPT-4
BenchmarkDeepSeek V4 Flash 0423GPT-4Leader
GPQA Diamond (Artificial Analysis run)Not measured34.9%Only GPT-4 measured
SimpleBench46.3%Not measuredOnly DeepSeek V4 Flash 0423 measured
BIG-Bench HardNot measured75.1%Only GPT-4 measured
LMArena Text: hard prompts14441200DeepSeek V4 Flash 0423
LMArena Text: expert14411149DeepSeek V4 Flash 0423
LMArena Text: hard prompts in English14491209DeepSeek V4 Flash 0423
Kagi LLM Benchmark52.2%Not measuredOnly DeepSeek V4 Flash 0423 measured
Neither model has a result on the other 15 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index20
Math benchmarks for DeepSeek V4 Flash 0423 and GPT-4
BenchmarkDeepSeek V4 Flash 0423GPT-4Leader
GSM8KNot measured92.0%Only GPT-4 measured
LMArena Text: math14261230DeepSeek V4 Flash 0423
LMArena Text: mathematical work14321228DeepSeek V4 Flash 0423
Neither model has a result on the other 10 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
Knowledge benchmarks for DeepSeek V4 Flash 0423 and GPT-4
BenchmarkDeepSeek V4 Flash 0423GPT-4Leader
MMLU Pro (Artificial Analysis run)Not measured56.2%Only GPT-4 measured
MMLUNot measured86.4%Only GPT-4 measured
AI2 Reasoning ChallengeNot measured96.3%Only GPT-4 measured
LMArena Text: science14461177DeepSeek V4 Flash 0423
LMArena Text: medicine and healthcare14481145DeepSeek V4 Flash 0423
LMArena Text: legal and government14391191DeepSeek V4 Flash 0423
LMArena Text: business and finance14251145DeepSeek V4 Flash 0423
Neither model has a result on the other 11 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for DeepSeek V4 Flash 0423 and GPT-4
BenchmarkDeepSeek V4 Flash 0423GPT-4Leader
Design Arena: websites1207Not measuredOnly DeepSeek V4 Flash 0423 measured
Design Arena: UI components1162Not measuredOnly DeepSeek V4 Flash 0423 measured
Design Arena: game dev1196Not measuredOnly DeepSeek V4 Flash 0423 measured
Design Arena: data viz1127Not measuredOnly DeepSeek V4 Flash 0423 measured
Design Arena: 3D1188Not measuredOnly DeepSeek V4 Flash 0423 measured
Design Arena: all code categories1205Not measuredOnly DeepSeek V4 Flash 0423 measured
Design Arena: SVG1155Not measuredOnly DeepSeek V4 Flash 0423 measured
Design Arena: ASCII art1109Not measuredOnly DeepSeek V4 Flash 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 Flash 0423 and GPT-4
BenchmarkDeepSeek V4 Flash 0423GPT-4Leader
IFBenchNot measured33.2%Only GPT-4 measured
DTBench86.4%62.7%DeepSeek V4 Flash 0423
LMCA35.9%17.1%DeepSeek V4 Flash 0423
HellaSwagNot measured95.3%Only GPT-4 measured
WinoGrandeNot measured87.5%Only GPT-4 measured
LMArena Text14321206DeepSeek V4 Flash 0423
LMArena Text: instruction following14211201DeepSeek V4 Flash 0423
LMArena Text: creative writing14031191DeepSeek V4 Flash 0423
LMArena Text: English14411220DeepSeek V4 Flash 0423
LMArena Text: non-English14191194DeepSeek V4 Flash 0423
LMArena Text: Chinese14631184DeepSeek V4 Flash 0423
LMArena Text: German14191198DeepSeek V4 Flash 0423
LMArena Text: Japanese13891137DeepSeek V4 Flash 0423
LMArena Text: Korean13831087DeepSeek V4 Flash 0423
LMArena Text: French14391220DeepSeek V4 Flash 0423
LMArena Text: Spanish14361197DeepSeek V4 Flash 0423
LMArena Text: Russian14271195DeepSeek V4 Flash 0423
LMArena Text: Polish14361265DeepSeek V4 Flash 0423
LMArena Text: multi-turn14491206DeepSeek V4 Flash 0423
LMArena Text: longer queries14341190DeepSeek V4 Flash 0423
LMArena Text: writing and language14101219DeepSeek V4 Flash 0423
LMArena Text: entertainment and media14001184DeepSeek V4 Flash 0423
Neither model has a result on the other 24 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for DeepSeek V4 Flash 0423 and GPT-4
BenchmarkDeepSeek V4 Flash 0423GPT-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 Flash 0423$0.0003Fits in one request
GPT-4$0.060Fits in one request

DeepSeek V4 Flash 0423 costs less

Repository review

50K input + 3K output tokens

DeepSeek V4 Flash 0423$0.0078Fits in one request
GPT-4$1.68Exceeds the context window

DeepSeek V4 Flash 0423 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V4 Flash 0423$0.031Fits in one request
GPT-4$6.60Exceeds the context window

DeepSeek V4 Flash 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 Flash 0423 and GPT-4
SpecificationDeepSeek V4 Flash 0423OpenAI GPT-4
MakerDeepSeekOpenAI
WeightsOpen weightsNo public weights listed
ReleasedApril 24, 2026May 28, 2023
Context window1.05M8K
Input $/Mtok$0.14$30.00
Output $/Mtok$0.28$60.00
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it10
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V4 Flash 0423 better than GPT-4 for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick DeepSeek V4 Flash 0423 for output tokens 214.3x cheaper ($0.28 vs $60.00 per million) and a larger context window (1.05M against 8K tokens).

Which is cheaper, DeepSeek V4 Flash 0423 or GPT-4?

DeepSeek V4 Flash 0423 costs $0.14 per million input tokens and $0.28 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 V4 Flash 0423 or GPT-4?

DeepSeek V4 Flash 0423, with 1.05M tokens against 8K.

How many benchmarks is the DeepSeek V4 Flash 0423 vs GPT-4 comparison based on?

33 benchmarks have a result for both models as of October 22, 2026. DeepSeek V4 Flash 0423's coding index rests on 1 independent benchmark and GPT-4's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next