Enter opens the highlighted result. Esc closes.

DeepSeek V4 Flash 0423 vs GPT-4o (2024-08-06)

DeepSeek V4 Flash 0423 leads GPT-4o (2024-08-06) on the Artificial Analysis Intelligence Index, 24.4 to 7.7, and DeepSeek V4 Flash 0423 costs 35.7x less per output token ($0.28 vs $10.00 per million). Updated October 22, 2026; 29 benchmarks have a result for both.

Replace DeepSeek V4 Flash 0423 Replace GPT-4o (2024-08-06)
DeepSeek V4 Flash 0423DeepSeek
Coding
No data
Overall
No data
Output $/M
$0.28
29
GPT-4o (2024-08-06)OpenAI
Coding
No data
Overall
26.3
Output $/M
$10.00
0
vs boards won of 29 shared

DeepSeek V4 Flash 0423 or GPT-4o (2024-08-06): 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 35.7x cheaper ($0.28 vs $10.00 per million) and a larger context window (1.05M against 128K tokens).

Model ADeepSeek V4 Flash 0423DeepSeekNot benchmarked1 independent benchmarkNo cost per solved taskModel BGPT-4o (2024-08-06)OpenAINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
29
DeepSeek V4 Flash 0423 only
20
GPT-4o (2024-08-06) only
29
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-4o (2024-08-06) not benchmarked.
Widest category
Knowledge, 30.2 points apart on average over 4 shared benchmarks.
Widest single gap
LMArena Text: Chinese: DeepSeek V4 Flash 0423 1463 against GPT-4o (2024-08-06) 1254, 34.8 points apart on a 0 to 100 scale.
Output price
DeepSeek V4 Flash 0423 $0.28 against GPT-4o (2024-08-06) $10.00 per million output tokens, 35.7x apart.
Context window
DeepSeek V4 Flash 0423 takes 1.05M tokens, GPT-4o (2024-08-06) 128K.

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-4o (2024-08-06)Ties
Coding20
Intelligence10
Reasoning40
Math20
Knowledge40
General160
All shared boards290
CodingLike-for-likeSix of these boards feed the Vibe Coding Index20
Coding benchmarks for DeepSeek V4 Flash 0423 and GPT-4o (2024-08-06)
BenchmarkDeepSeek V4 Flash 0423GPT-4o (2024-08-06)Leader
Aider polyglotNot measured23.1%Only GPT-4o (2024-08-06) measured
SWE-bench LiteNot measured21.7%Only GPT-4o (2024-08-06) measured
LMArena WebDev1582Not measuredOnly DeepSeek V4 Flash 0423 measured
AA Coding Index52.0Not measuredOnly DeepSeek V4 Flash 0423 measured
LiveCodeBench (Artificial Analysis run)Not measured31.7%Only GPT-4o (2024-08-06) measured
Terminal-Bench Hard (Artificial Analysis run)Not measured8.3%Only GPT-4o (2024-08-06) measured
WeirdML45.6%Not measuredOnly DeepSeek V4 Flash 0423 measured
ALE-Bench678.2Not measuredOnly DeepSeek V4 Flash 0423 measured
LMArena Text: coding14571283DeepSeek V4 Flash 0423
LMArena Text: software and IT14531278DeepSeek 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 27 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for DeepSeek V4 Flash 0423 and GPT-4o (2024-08-06)
BenchmarkDeepSeek V4 Flash 0423GPT-4o (2024-08-06)Leader
AA Intelligence Index24.47.7DeepSeek V4 Flash 0423
Epoch Capabilities Index146.1Not measuredOnly DeepSeek V4 Flash 0423 measured
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Agentic work benchmarks for DeepSeek V4 Flash 0423 and GPT-4o (2024-08-06)
BenchmarkDeepSeek V4 Flash 0423GPT-4o (2024-08-06)Leader
AA Agentic Index26.3Not measuredOnly DeepSeek V4 Flash 0423 measured
τ²-Bench TelecomNot measured28.9%Only GPT-4o (2024-08-06) measured
Neither model has a result on the other 39 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index40
Reasoning benchmarks for DeepSeek V4 Flash 0423 and GPT-4o (2024-08-06)
BenchmarkDeepSeek V4 Flash 0423GPT-4o (2024-08-06)Leader
MMMU Pro (Vals AI)Not measured64.0%Only GPT-4o (2024-08-06) measured
GPQA Diamond (Artificial Analysis run)Not measured52.1%Only GPT-4o (2024-08-06) measured
Humanity's Last Exam (Artificial Analysis run)Not measured2.3%Only GPT-4o (2024-08-06) measured
GPQA Diamond (Epoch AI run)Not measured49.2%Only GPT-4o (2024-08-06) measured
SimpleBench46.3%17.8%DeepSeek V4 Flash 0423
Chess puzzlesNot measured6.0%Only GPT-4o (2024-08-06) measured
LMArena Text: hard prompts14441264DeepSeek V4 Flash 0423
LMArena Text: expert14411241DeepSeek V4 Flash 0423
LMArena Text: hard prompts in English14491277DeepSeek V4 Flash 0423
Kagi LLM Benchmark52.2%Not measuredOnly DeepSeek V4 Flash 0423 measured
Neither model has a result on the other 12 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index20
Math benchmarks for DeepSeek V4 Flash 0423 and GPT-4o (2024-08-06)
BenchmarkDeepSeek V4 Flash 0423GPT-4o (2024-08-06)Leader
AIMENot measured14.0%Only GPT-4o (2024-08-06) measured
MATH 500 (Vals AI)Not measured75.2%Only GPT-4o (2024-08-06) measured
MGSM (Vals AI)Not measured90.7%Only GPT-4o (2024-08-06) measured
OTIS Mock AIMENot measured6.4%Only GPT-4o (2024-08-06) measured
FrontierMath, tiers 1 to 3Not measured0.4%Only GPT-4o (2024-08-06) measured
MATH level 5Not measured53.3%Only GPT-4o (2024-08-06) measured
LMArena Text: math14261285DeepSeek V4 Flash 0423
LMArena Text: mathematical work14321283DeepSeek V4 Flash 0423
Neither model has a result on the other 5 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
Knowledge benchmarks for DeepSeek V4 Flash 0423 and GPT-4o (2024-08-06)
BenchmarkDeepSeek V4 Flash 0423GPT-4o (2024-08-06)Leader
MMLU ProNot measured74.1%Only GPT-4o (2024-08-06) measured
LegalBench (Vals AI)Not measured80.1%Only GPT-4o (2024-08-06) measured
CorpFin (Vals AI)Not measured39.4%Only GPT-4o (2024-08-06) measured
TaxEval (Vals AI)Not measured71.1%Only GPT-4o (2024-08-06) measured
MortgageTax (Vals AI)Not measured61.0%Only GPT-4o (2024-08-06) measured
MedQA (Vals AI)Not measured88.2%Only GPT-4o (2024-08-06) measured
SimpleQA VerifiedNot measured26.0%Only GPT-4o (2024-08-06) measured
MMLUNot measured84.3%Only GPT-4o (2024-08-06) measured
LMArena Text: science14461274DeepSeek V4 Flash 0423
LMArena Text: medicine and healthcare14481252DeepSeek V4 Flash 0423
LMArena Text: legal and government14391275DeepSeek V4 Flash 0423
LMArena Text: business and finance14251232DeepSeek V4 Flash 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 Flash 0423 and GPT-4o (2024-08-06)
BenchmarkDeepSeek V4 Flash 0423GPT-4o (2024-08-06)Leader
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 index160
General benchmarks for DeepSeek V4 Flash 0423 and GPT-4o (2024-08-06)
BenchmarkDeepSeek V4 Flash 0423GPT-4o (2024-08-06)Leader
IFBenchNot measured36.0%Only GPT-4o (2024-08-06) measured
Long context reasoning (AA-LCR)Not measured41.0%Only GPT-4o (2024-08-06) measured
DTBench86.4%Not measuredOnly DeepSeek V4 Flash 0423 measured
LMCA35.9%Not measuredOnly DeepSeek V4 Flash 0423 measured
LMArena Text14321283DeepSeek V4 Flash 0423
LMArena Text: instruction following14211267DeepSeek V4 Flash 0423
LMArena Text: creative writing14031274DeepSeek V4 Flash 0423
LMArena VisionNot measured1065Only GPT-4o (2024-08-06) measured
LMArena Text: English14411297DeepSeek V4 Flash 0423
LMArena Text: non-English14191262DeepSeek V4 Flash 0423
LMArena Text: Chinese14631254DeepSeek V4 Flash 0423
LMArena Text: German14191257DeepSeek V4 Flash 0423
LMArena Text: Japanese13891234DeepSeek V4 Flash 0423
LMArena Text: Korean13831218DeepSeek V4 Flash 0423
LMArena Text: French14391263DeepSeek V4 Flash 0423
LMArena Text: Spanish14361269DeepSeek V4 Flash 0423
LMArena Text: Russian14271272DeepSeek V4 Flash 0423
LMArena Text: Polish1436Not measuredOnly DeepSeek V4 Flash 0423 measured
LMArena Text: multi-turn14491279DeepSeek V4 Flash 0423
LMArena Text: longer queries14341283DeepSeek V4 Flash 0423
LMArena Text: writing and language14101290DeepSeek V4 Flash 0423
LMArena Text: entertainment and media14001267DeepSeek V4 Flash 0423
LMArena Vision: EnglishNot measured1072Only GPT-4o (2024-08-06) measured
LMArena Vision: ChineseNot measured1009Only GPT-4o (2024-08-06) measured
Neither model has a result on the other 22 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-4o (2024-08-06)
BenchmarkDeepSeek V4 Flash 0423GPT-4o (2024-08-06)Leader
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-4o (2024-08-06)$0.0075Fits 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-4o (2024-08-06)$0.155Fits in one request

DeepSeek V4 Flash 0423 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V4 Flash 0423$0.031Fits in one request
GPT-4o (2024-08-06)$0.600Exceeds 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-4o (2024-08-06)
SpecificationDeepSeek V4 Flash 0423OpenAI GPT-4o (2024-08-06)
MakerDeepSeekOpenAI
WeightsOpen weightsNo public weights listed
ReleasedApril 24, 2026August 6, 2024
Context window1.05M128K
Input $/Mtok$0.14$2.50
Output $/Mtok$0.28$10.00
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-4o (2024-08-06) 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 35.7x cheaper ($0.28 vs $10.00 per million) and a larger context window (1.05M against 128K tokens).

Which is cheaper, DeepSeek V4 Flash 0423 or GPT-4o (2024-08-06)?

DeepSeek V4 Flash 0423 costs $0.14 per million input tokens and $0.28 per million output tokens; GPT-4o (2024-08-06) costs $2.50 and $10.00. Cost per solved task is known for neither of them.

Which has the bigger context window, DeepSeek V4 Flash 0423 or GPT-4o (2024-08-06)?

DeepSeek V4 Flash 0423, with 1.05M tokens against 128K.

How many benchmarks is the DeepSeek V4 Flash 0423 vs GPT-4o (2024-08-06) comparison based on?

29 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-4o (2024-08-06)'s on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next