Enter opens the highlighted result. Esc closes.

GPT-4 vs GPT-4o-mini (2024-07-18)

GPT-4o-mini (2024-07-18) costs 100.0x less per output token than GPT-4 ($0.60 vs $60.00 per million). Updated October 22, 2026; 29 benchmarks have a result for both.

Replace GPT-4 Replace GPT-4o-mini (2024-07-18)
GPT-4OpenAI
Coding
No data
Overall
No data
Output $/M
$60.00
2
GPT-4o-mini (2024-07-18)OpenAI
Coding
No data
Overall
No data
Output $/M
$0.60
27
vs boards won of 29 shared

GPT-4 or GPT-4o-mini (2024-07-18): 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 LMArena Text: coding or LMArena Text: software and IT, where it leads.

Model AGPT-4OpenAINot benchmarkedNo coding benchmarkNo cost per solved taskModel BGPT-4o-mini (2024-07-18)OpenAINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
29
GPT-4 only
16
GPT-4o-mini (2024-07-18) only
17
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
GPT-4 not benchmarked, GPT-4o-mini (2024-07-18) not benchmarked.
Widest category
Knowledge, 17.9 points apart on average over 5 shared benchmarks.
Widest single gap
LMArena Text: medicine and healthcare: GPT-4 1145 against GPT-4o-mini (2024-07-18) 1282, 22.8 points apart on a 0 to 100 scale.
Output price
GPT-4 $60.00 against GPT-4o-mini (2024-07-18) $0.60 per million output tokens, 100.0x apart.
Context window
GPT-4 takes 8K tokens, GPT-4o-mini (2024-07-18) 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-mini (2024-07-18)Ties
Coding02
Reasoning03
Math02
Knowledge14
General116
All shared boards227
CodingLike-for-likeSix of these boards feed the Vibe Coding Index02
Coding benchmarks for GPT-4 and GPT-4o-mini (2024-07-18)
BenchmarkGPT-4GPT-4o-mini (2024-07-18)Leader
Aider polyglotNot measured3.6%Only GPT-4o-mini (2024-07-18) measured
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 Index13.1Not measuredOnly GPT-4 measured
WeirdMLNot measured11.8%Only GPT-4o-mini (2024-07-18) measured
LMArena Text: coding12091290GPT-4o-mini (2024-07-18)
LMArena Text: software and IT11951291GPT-4o-mini (2024-07-18)
Neither model has a result on the other 31 boards here
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Intelligence benchmarks for GPT-4 and GPT-4o-mini (2024-07-18)
BenchmarkGPT-4GPT-4o-mini (2024-07-18)Leader
AA Intelligence Index6.7Not measuredOnly GPT-4 measured
Epoch Capabilities Index125.7Not measuredOnly GPT-4 measured
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
Agentic work benchmarks for GPT-4 and GPT-4o-mini (2024-07-18)
BenchmarkGPT-4GPT-4o-mini (2024-07-18)Leader
BALROGNot measured17.4%Only GPT-4o-mini (2024-07-18) measured
Neither model has a result on the other 40 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index03
Reasoning benchmarks for GPT-4 and GPT-4o-mini (2024-07-18)
BenchmarkGPT-4GPT-4o-mini (2024-07-18)Leader
GPQA Diamond (Artificial Analysis run)34.9%Not measuredOnly GPT-4 measured
GPQA Diamond (Epoch AI run)Not measured37.7%Only GPT-4o-mini (2024-07-18) measured
SimpleBenchNot measured10.7%Only GPT-4o-mini (2024-07-18) measured
Chess puzzlesNot measured3.0%Only GPT-4o-mini (2024-07-18) measured
Mystery game puzzlesNot measured12.0%Only GPT-4o-mini (2024-07-18) measured
VPCTNot measured34.0%Only GPT-4o-mini (2024-07-18) measured
BIG-Bench Hard75.1%Not measuredOnly GPT-4 measured
LMArena Text: hard prompts12001267GPT-4o-mini (2024-07-18)
LMArena Text: expert11491234GPT-4o-mini (2024-07-18)
LMArena Text: hard prompts in English12091278GPT-4o-mini (2024-07-18)
Neither model has a result on the other 12 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for GPT-4 and GPT-4o-mini (2024-07-18)
BenchmarkGPT-4GPT-4o-mini (2024-07-18)Leader
OTIS Mock AIMENot measured6.9%Only GPT-4o-mini (2024-07-18) measured
FrontierMath, tiers 1 to 3Not measured0.7%Only GPT-4o-mini (2024-07-18) measured
MATH level 5Not measured52.6%Only GPT-4o-mini (2024-07-18) measured
GSM8K92.0%Not measuredOnly GPT-4 measured
LMArena Text: math12301267GPT-4o-mini (2024-07-18)
LMArena Text: mathematical work12281271GPT-4o-mini (2024-07-18)
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index14
Knowledge benchmarks for GPT-4 and GPT-4o-mini (2024-07-18)
BenchmarkGPT-4GPT-4o-mini (2024-07-18)Leader
MMLU Pro (Artificial Analysis run)56.2%Not measuredOnly GPT-4 measured
SimpleQA VerifiedNot measured8.3%Only GPT-4o-mini (2024-07-18) measured
MMLU86.4%76.7%GPT-4
GeoBenchNot measured64.0%Only GPT-4o-mini (2024-07-18) measured
AI2 Reasoning Challenge96.3%Not measuredOnly GPT-4 measured
LMArena Text: science11771286GPT-4o-mini (2024-07-18)
LMArena Text: medicine and healthcare11451282GPT-4o-mini (2024-07-18)
LMArena Text: legal and government11911305GPT-4o-mini (2024-07-18)
LMArena Text: business and finance11451265GPT-4o-mini (2024-07-18)
Neither model has a result on the other 9 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-mini (2024-07-18)
BenchmarkGPT-4GPT-4o-mini (2024-07-18)Leader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index116
General benchmarks for GPT-4 and GPT-4o-mini (2024-07-18)
BenchmarkGPT-4GPT-4o-mini (2024-07-18)Leader
IFBench33.2%Not measuredOnly GPT-4 measured
DTBench62.7%Not measuredOnly GPT-4 measured
LMCA17.1%Not measuredOnly GPT-4 measured
Creative writing (Lech Mazur)Not measured67.2%Only GPT-4o-mini (2024-07-18) measured
HellaSwag95.3%Not measuredOnly GPT-4 measured
WinoGrande87.5%Not measuredOnly GPT-4 measured
LMArena Text12061286GPT-4o-mini (2024-07-18)
LMArena Text: instruction following12011258GPT-4o-mini (2024-07-18)
LMArena Text: creative writing11911268GPT-4o-mini (2024-07-18)
LMArena VisionNot measured1066Only GPT-4o-mini (2024-07-18) measured
LMArena Text: English12201301GPT-4o-mini (2024-07-18)
LMArena Text: non-English11941266GPT-4o-mini (2024-07-18)
LMArena Text: Chinese11841265GPT-4o-mini (2024-07-18)
LMArena Text: German11981272GPT-4o-mini (2024-07-18)
LMArena Text: Japanese11371216GPT-4o-mini (2024-07-18)
LMArena Text: Korean10871195GPT-4o-mini (2024-07-18)
LMArena Text: French12201297GPT-4o-mini (2024-07-18)
LMArena Text: Spanish11971276GPT-4o-mini (2024-07-18)
LMArena Text: Russian11951275GPT-4o-mini (2024-07-18)
LMArena Text: Polish12651244GPT-4
LMArena Text: multi-turn12061285GPT-4o-mini (2024-07-18)
LMArena Text: longer queries11901289GPT-4o-mini (2024-07-18)
LMArena Text: writing and language12191282GPT-4o-mini (2024-07-18)
LMArena Text: entertainment and media11841253GPT-4o-mini (2024-07-18)
LMArena Vision: EnglishNot measured1072Only GPT-4o-mini (2024-07-18) measured
LMArena Vision: ChineseNot measured1033Only GPT-4o-mini (2024-07-18) measured
Neither model has a result on the other 20 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-mini (2024-07-18)
BenchmarkGPT-4GPT-4o-mini (2024-07-18)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-mini (2024-07-18)$0.0004Fits in one request

GPT-4o-mini (2024-07-18) costs less

Repository review

50K input + 3K output tokens

GPT-4$1.68Exceeds the context window
GPT-4o-mini (2024-07-18)$0.0093Fits in one request

GPT-4o-mini (2024-07-18) costs less

Agent loop

200K input + 10K output tokens

GPT-4$6.60Exceeds the context window
GPT-4o-mini (2024-07-18)$0.036Exceeds the context window

GPT-4o-mini (2024-07-18) 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-mini (2024-07-18)
SpecificationOpenAI GPT-4OpenAI GPT-4o-mini (2024-07-18)
MakerOpenAIOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedMay 28, 2023July 18, 2024
Context window8K128K
Input $/Mtok$30.00$0.15
Output $/Mtok$60.00$0.60
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-mini (2024-07-18) for coding?

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

Which is cheaper, GPT-4 or GPT-4o-mini (2024-07-18)?

GPT-4 costs $30.00 per million input tokens and $60.00 per million output tokens; GPT-4o-mini (2024-07-18) costs $0.15 and $0.60. Cost per solved task is known for neither of them.

Which has the bigger context window, GPT-4 or GPT-4o-mini (2024-07-18)?

GPT-4o-mini (2024-07-18), with 128K tokens against 8K.

How many benchmarks is the GPT-4 vs GPT-4o-mini (2024-07-18) comparison based on?

29 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-mini (2024-07-18)'s on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next