Enter opens the highlighted result. Esc closes.

GPT-4 vs GPT-4o (2024-05-13)

GPT-4o (2024-05-13) leads GPT-4 on the Artificial Analysis Intelligence Index, 7.3 to 6.7, and GPT-4o (2024-05-13) costs 4.0x less per output token ($15.00 vs $60.00 per million). Updated October 22, 2026; 33 benchmarks have a result for both.

Replace GPT-4 Replace GPT-4o (2024-05-13)
GPT-4OpenAI
Coding
No data
Overall
No data
Output $/M
$60.00
1
GPT-4o (2024-05-13)OpenAI
Coding
No data
Overall
27.1
Output $/M
$15.00
32
vs boards won of 33 shared

GPT-4 or GPT-4o (2024-05-13): which to pick

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

Pick GPT-4 for work measured by AA Coding Index or LMArena Text: coding, where it leads.

Model AGPT-4OpenAINot benchmarkedNo coding benchmarkNo cost per solved taskModel BGPT-4o (2024-05-13)OpenAINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
33
GPT-4 only
12
GPT-4o (2024-05-13) only
11
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
GPT-4 not benchmarked, GPT-4o (2024-05-13) not benchmarked.
Widest category
Knowledge, 16.9 points apart on average over 6 shared benchmarks.
Widest single gap
LMArena Text: Korean: GPT-4 1087 against GPT-4o (2024-05-13) 1234, 24.5 points apart on a 0 to 100 scale.
Output price
GPT-4 $60.00 against GPT-4o (2024-05-13) $15.00 per million output tokens, 4.0x apart.
Context window
GPT-4 takes 8K tokens, GPT-4o (2024-05-13) 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
CategoryGPT-4BarsGPT-4o (2024-05-13)Ties
Coding03
Intelligence01
Reasoning04
Math02
Knowledge15
General017
All shared boards132
CodingLike-for-likeSix of these boards feed the Vibe Coding Index03
Coding benchmarks for GPT-4 and GPT-4o (2024-05-13)
BenchmarkGPT-4GPT-4o (2024-05-13)Leader
SWE-bench Verified22.4%Not measuredOnly GPT-4 measured
SWE-bench Lite39.7%Not measuredOnly GPT-4 measured
SWE-bench (full test set)12.5%Not measuredOnly GPT-4 measured
AA Coding Index13.124.2GPT-4o (2024-05-13)
LiveCodeBench (Artificial Analysis run)Not measured33.4%Only GPT-4o (2024-05-13) measured
LMArena Text: coding12091297GPT-4o (2024-05-13)
LMArena Text: software and IT11951297GPT-4o (2024-05-13)
Neither model has a result on the other 36 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for GPT-4 and GPT-4o (2024-05-13)
BenchmarkGPT-4GPT-4o (2024-05-13)Leader
AA Intelligence Index6.77.3GPT-4o (2024-05-13)
Epoch Capabilities Index125.7Not measuredOnly GPT-4 measured
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Agentic work benchmarks for GPT-4 and GPT-4o (2024-05-13)
BenchmarkGPT-4GPT-4o (2024-05-13)Leader
METR time horizonsNot measured40.8%Only GPT-4o (2024-05-13) measured
BALROGNot measured32.3%Only GPT-4o (2024-05-13) measured
Neither model has a result on the other 40 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index04
Reasoning benchmarks for GPT-4 and GPT-4o (2024-05-13)
BenchmarkGPT-4GPT-4o (2024-05-13)Leader
GPQA DiamondNot measured50.2%Only GPT-4o (2024-05-13) measured
GPQA Diamond (Artificial Analysis run)34.9%52.6%GPT-4o (2024-05-13)
Humanity's Last Exam (Artificial Analysis run)Not measured1.8%Only GPT-4o (2024-05-13) measured
GPQA Diamond (Epoch AI run)Not measured48.9%Only GPT-4o (2024-05-13) measured
BIG-Bench Hard75.1%Not measuredOnly GPT-4 measured
LMArena Text: hard prompts12001281GPT-4o (2024-05-13)
LMArena Text: expert11491250GPT-4o (2024-05-13)
LMArena Text: hard prompts in English12091293GPT-4o (2024-05-13)
Neither model has a result on the other 15 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for GPT-4 and GPT-4o (2024-05-13)
BenchmarkGPT-4GPT-4o (2024-05-13)Leader
OTIS Mock AIMENot measured6.3%Only GPT-4o (2024-05-13) measured
MATH level 5Not measured51.0%Only GPT-4o (2024-05-13) measured
GSM8K92.0%Not measuredOnly GPT-4 measured
LMArena Text: math12301284GPT-4o (2024-05-13)
LMArena Text: mathematical work12281284GPT-4o (2024-05-13)
Neither model has a result on the other 9 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index15
Knowledge benchmarks for GPT-4 and GPT-4o (2024-05-13)
BenchmarkGPT-4GPT-4o (2024-05-13)Leader
MMLU Pro (Artificial Analysis run)56.2%74.0%GPT-4o (2024-05-13)
MMLU86.4%84.2%GPT-4
AI2 Reasoning Challenge96.3%Not measuredOnly GPT-4 measured
LMArena Text: science11771295GPT-4o (2024-05-13)
LMArena Text: medicine and healthcare11451278GPT-4o (2024-05-13)
LMArena Text: legal and government11911314GPT-4o (2024-05-13)
LMArena Text: business and finance11451262GPT-4o (2024-05-13)
Neither model has a result on the other 13 boards here
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Web design benchmarks for GPT-4 and GPT-4o (2024-05-13)
BenchmarkGPT-4GPT-4o (2024-05-13)Leader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index017
General benchmarks for GPT-4 and GPT-4o (2024-05-13)
BenchmarkGPT-4GPT-4o (2024-05-13)Leader
IFBench33.2%Not measuredOnly GPT-4 measured
DTBench62.7%Not measuredOnly GPT-4 measured
LMCA17.1%Not measuredOnly GPT-4 measured
HellaSwag95.3%Not measuredOnly GPT-4 measured
WinoGrande87.5%Not measuredOnly GPT-4 measured
LMArena Text12061300GPT-4o (2024-05-13)
LMArena Text: instruction following12011278GPT-4o (2024-05-13)
LMArena Text: creative writing11911291GPT-4o (2024-05-13)
LMArena VisionNot measured1137Only GPT-4o (2024-05-13) measured
LMArena Text: English12201312GPT-4o (2024-05-13)
LMArena Text: non-English11941283GPT-4o (2024-05-13)
LMArena Text: Chinese11841277GPT-4o (2024-05-13)
LMArena Text: German11981283GPT-4o (2024-05-13)
LMArena Text: Japanese11371257GPT-4o (2024-05-13)
LMArena Text: Korean10871234GPT-4o (2024-05-13)
LMArena Text: French12201304GPT-4o (2024-05-13)
LMArena Text: Spanish11971292GPT-4o (2024-05-13)
LMArena Text: Russian11951285GPT-4o (2024-05-13)
LMArena Text: Polish12651365GPT-4o (2024-05-13)
LMArena Text: multi-turn12061302GPT-4o (2024-05-13)
LMArena Text: longer queries11901288GPT-4o (2024-05-13)
LMArena Text: writing and language12191298GPT-4o (2024-05-13)
LMArena Text: entertainment and media11841289GPT-4o (2024-05-13)
LMArena Vision: EnglishNot measured1147Only GPT-4o (2024-05-13) measured
LMArena Vision: ChineseNot measured1132Only GPT-4o (2024-05-13) measured
Neither model has a result on the other 23 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-4 and GPT-4o (2024-05-13)
BenchmarkGPT-4GPT-4o (2024-05-13)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

GPT-4$0.060Fits in one request
GPT-4o (2024-05-13)$0.013Fits in one request

GPT-4o (2024-05-13) costs less

Repository review

50K input + 3K output tokens

GPT-4$1.68Exceeds the context window
GPT-4o (2024-05-13)$0.295Fits in one request

GPT-4o (2024-05-13) costs less

Agent loop

200K input + 10K output tokens

GPT-4$6.60Exceeds the context window
GPT-4o (2024-05-13)$1.15Exceeds the context window

GPT-4o (2024-05-13) 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 GPT-4 and GPT-4o (2024-05-13)
SpecificationOpenAI GPT-4OpenAI GPT-4o (2024-05-13)
MakerOpenAIOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedMay 28, 2023May 13, 2024
Context window8K128K
Input $/Mtok$30.00$5.00
Output $/Mtok$60.00$15.00
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-4 better than GPT-4o (2024-05-13) for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GPT-4 for work measured by AA Coding Index or LMArena Text: coding, where it leads.

Which is cheaper, GPT-4 or GPT-4o (2024-05-13)?

GPT-4 costs $30.00 per million input tokens and $60.00 per million output tokens; GPT-4o (2024-05-13) costs $5.00 and $15.00. Cost per solved task is known for neither of them.

Which has the bigger context window, GPT-4 or GPT-4o (2024-05-13)?

GPT-4o (2024-05-13), with 128K tokens against 8K.

How many benchmarks is the GPT-4 vs GPT-4o (2024-05-13) comparison based on?

33 benchmarks have a result for both models as of October 22, 2026. GPT-4's coding index rests on 0 independent benchmarks and GPT-4o (2024-05-13)'s on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next