Enter opens the highlighted result. Esc closes.

GPT-4o (2024-08-06) vs GPT-5

GPT-5 leads GPT-4o (2024-08-06) on the Artificial Analysis Intelligence Index, 23.0 to 7.7, at about the same output price ($10.00 vs $10.00 per million). Updated October 22, 2026; 56 benchmarks have a result for both.

Replace GPT-4o (2024-08-06) Replace GPT-5
GPT-4o (2024-08-06)OpenAI
Coding
No data
Overall
26.3
Output $/M
$10.00
0
GPT-5OpenAI
Coding
38.8
Overall
51.5
Output $/M
$10.00
56
vs boards won of 56 shared

GPT-4o (2024-08-06) or GPT-5: which to pick

Only GPT-5 has a coding score, 38.8 on the Vibe Coding Index; GPT-4o (2024-08-06) has none, so the two cannot be ranked on coding.

Compare them on price, context and the boards below.

Model AGPT-4o (2024-08-06)OpenAINot benchmarkedNo coding benchmarkNo cost per solved taskModel BGPT-5OpenAI38.8/1003 independent benchmarks$0.39 per solved task
Shared results
56
GPT-4o (2024-08-06) only
2
GPT-5 only
61
Like-for-like categories
7 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-4o (2024-08-06) not benchmarked, GPT-5 38.8 from 3 benchmarks.
Widest category
Agentic work, 57.6 points apart on average over 1 shared benchmark.
Widest single gap
OTIS Mock AIME: GPT-4o (2024-08-06) 6.4% against GPT-5 91.4%, 85.0 points apart on a 0 to 100 scale.
Output price
Both cost $10.00 per million output tokens.
Context window
GPT-4o (2024-08-06) takes 128K tokens, GPT-5 400K.

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-4o (2024-08-06)BarsGPT-5Ties
Coding05
Intelligence01
Agentic work01
Reasoning09
Math08
Knowledge011
General021
All shared boards056
CodingLike-for-likeSix of these boards feed the Vibe Coding Index05
Coding benchmarks for GPT-4o (2024-08-06) and GPT-5
BenchmarkGPT-4o (2024-08-06)GPT-5Leader
Aider polyglot23.1%88.0%GPT-5
SWE-bench VerifiedNot measured74.4%Only GPT-5 measured
SWE-bench Lite21.7%Not measuredOnly GPT-4o (2024-08-06) measured
LMArena WebDevNot measured1418Only GPT-5 measured
AA Coding IndexNot measured37.8Only GPT-5 measured
LiveCodeBench (Vals AI)Not measured85.9%Only GPT-5 measured
SWE-bench Verified (Vals AI)Not measured69.0%Only GPT-5 measured
Vibe Code Bench (Vals AI)Not measured20.1%Only GPT-5 measured
LiveCodeBench (Artificial Analysis run)31.7%84.6%GPT-5
Terminal-Bench Hard (Artificial Analysis run)8.3%37.9%GPT-5
Terminal-BenchNot measured49.6%Only GPT-5 measured
GSO-BenchNot measured6.9%Only GPT-5 measured
WeirdMLNot measured60.7%Only GPT-5 measured
ALE-BenchNot measured807.6Only GPT-5 measured
LMArena Text: coding12831436GPT-5
LMArena Text: software and IT12781420GPT-5
LMArena WebDev: HTMLNot measured1427Only GPT-5 measured
SciCodeNot measured0.0%Only GPT-5 measured
Neither model has a result on the other 25 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for GPT-4o (2024-08-06) and GPT-5
BenchmarkGPT-4o (2024-08-06)GPT-5Leader
AA Intelligence Index7.723.0GPT-5
Epoch Capabilities IndexNot measured150.0Only GPT-5 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for GPT-4o (2024-08-06) and GPT-5
BenchmarkGPT-4o (2024-08-06)GPT-5Leader
τ²-Bench Telecom28.9%86.5%GPT-5
METR time horizonsNot measured69.6%Only GPT-5 measured
Remote Labor IndexNot measured1.7%Only GPT-5 measured
GDPvalNot measured34.8%Only GPT-5 measured
BALROGNot measured32.8%Only GPT-5 measured
DeepResearch BenchNot measured49.6%Only GPT-5 measured
BrowseComp-PlusNot measured80.0%Only GPT-5 measured
Neither model has a result on the other 35 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index09
Reasoning benchmarks for GPT-4o (2024-08-06) and GPT-5
BenchmarkGPT-4o (2024-08-06)GPT-5Leader
GPQA DiamondNot measured85.6%Only GPT-5 measured
MMMU Pro (Vals AI)64.0%81.5%GPT-5
GPQA Diamond (Artificial Analysis run)52.1%85.4%GPT-5
Humanity's Last Exam (Artificial Analysis run)2.3%28.5%GPT-5
GPQA Diamond (Epoch AI run)49.2%86.2%GPT-5
ARC-AGINot measured65.7%Only GPT-5 measured
ARC-AGI-2Not measured9.9%Only GPT-5 measured
SimpleBench17.8%56.7%GPT-5
Chess puzzles6.0%36.0%GPT-5
Mystery game puzzlesNot measured23.0%Only GPT-5 measured
EBR-benchNot measured12.7%Only GPT-5 measured
VPCTNot measured66.0%Only GPT-5 measured
LMArena Text: hard prompts12641415GPT-5
LMArena Text: expert12411419GPT-5
LMArena Text: hard prompts in English12771419GPT-5
LMArena Vision: diagramsNot measured1252Only GPT-5 measured
LMArena Vision: homeworkNot measured1278Only GPT-5 measured
Kagi LLM BenchmarkNot measured72.7%Only GPT-5 measured
Neither model has a result on the other 5 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index08
Math benchmarks for GPT-4o (2024-08-06) and GPT-5
BenchmarkGPT-4o (2024-08-06)GPT-5Leader
AIME14.0%93.4%GPT-5
MATH 500 (Vals AI)75.2%96.0%GPT-5
MGSM (Vals AI)90.7%92.8%GPT-5
AA Math IndexNot measured94.3Only GPT-5 measured
AIME 2025 (Artificial Analysis run)Not measured94.3%Only GPT-5 measured
OTIS Mock AIME6.4%91.4%GPT-5
FrontierMath, tiers 1 to 30.4%55.4%GPT-5
FrontierMath, tier 4Not measured22.0%Only GPT-5 measured
ProofBenchNot measured18.0%Only GPT-5 measured
MATH level 553.3%98.1%GPT-5
LMArena Text: math12851407GPT-5
LMArena Text: mathematical work12831405GPT-5
MathArenaNot measured17.1%Only GPT-5 measured
Neither model has a result on the other 1 board here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index011
Knowledge benchmarks for GPT-4o (2024-08-06) and GPT-5
BenchmarkGPT-4o (2024-08-06)GPT-5Leader
MMLU Pro74.1%86.5%GPT-5
LegalBench (Vals AI)80.1%86.0%GPT-5
CaseLaw (Vals AI)Not measured66.5%Only GPT-5 measured
CorpFin (Vals AI)39.4%61.1%GPT-5
TaxEval (Vals AI)71.1%73.4%GPT-5
MortgageTax (Vals AI)61.0%65.5%GPT-5
MedQA (Vals AI)88.2%96.3%GPT-5
MedCode (Vals AI)Not measured49.6%Only GPT-5 measured
MMLU Pro (Artificial Analysis run)Not measured87.1%Only GPT-5 measured
SimpleQA Verified26.0%50.1%GPT-5
MMLU84.3%Not measuredOnly GPT-4o (2024-08-06) measured
GeoBenchNot measured81.0%Only GPT-5 measured
LMArena Text: science12741416GPT-5
LMArena Text: medicine and healthcare12521413GPT-5
LMArena Text: legal and government12751431GPT-5
LMArena Text: business and finance12321400GPT-5
FACTS Benchmark SuiteNot measured56.5%Only GPT-5 measured
PRBench FinanceNot measured51.3%Only GPT-5 measured
PRBench LegalNot measured49.0%Only GPT-5 measured
Neither model has a result on the other 1 board here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for GPT-4o (2024-08-06) and GPT-5
BenchmarkGPT-4o (2024-08-06)GPT-5Leader
Design Arena: websitesNot measured1184Only GPT-5 measured
Design Arena: UI componentsNot measured1177Only GPT-5 measured
Design Arena: game devNot measured1185Only GPT-5 measured
Design Arena: data vizNot measured1221Only GPT-5 measured
Design Arena: 3DNot measured1055Only GPT-5 measured
Design Arena: all code categoriesNot measured1167Only GPT-5 measured
Design Arena: SVGNot measured1188Only GPT-5 measured
Design Arena: ASCII artNot measured1141Only GPT-5 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index021
General benchmarks for GPT-4o (2024-08-06) and GPT-5
BenchmarkGPT-4o (2024-08-06)GPT-5Leader
SAGE (Vals AI)Not measured43.7%Only GPT-5 measured
MedScribe (Vals AI)Not measured83.7%Only GPT-5 measured
IFBench36.0%73.1%GPT-5
Long context reasoning (AA-LCR)41.0%78.2%GPT-5
DTBenchNot measured90.7%Only GPT-5 measured
LMCANot measured40.0%Only GPT-5 measured
Fiction.LiveBenchNot measured97.2%Only GPT-5 measured
Creative writing (Lech Mazur)Not measured86.0%Only GPT-5 measured
LMArena Text12831406GPT-5
LMArena Text: instruction following12671388GPT-5
LMArena Text: creative writing12741365GPT-5
LMArena Vision10651232GPT-5
LMArena Text: English12971409GPT-5
LMArena Text: non-English12621397GPT-5
LMArena Text: Chinese12541422GPT-5
LMArena Text: German12571416GPT-5
LMArena Text: Japanese12341409GPT-5
LMArena Text: Korean12181360GPT-5
LMArena Text: French12631409GPT-5
LMArena Text: Spanish12691399GPT-5
LMArena Text: Russian12721407GPT-5
LMArena Text: PolishNot measured1431Only GPT-5 measured
LMArena Text: multi-turn12791426GPT-5
LMArena Text: longer queries12831399GPT-5
LMArena Text: writing and language12901384GPT-5
LMArena Text: entertainment and media12671379GPT-5
LMArena Vision: English10721231GPT-5
LMArena Vision: Chinese10091267GPT-5
LMArena Vision: reading textNot measured1246Only GPT-5 measured
LMArena Vision: humorNot measured1219Only GPT-5 measured
LMArena Vision: captioningNot measured1212Only GPT-5 measured
LMArena Vision: recognizing thingsNot measured1263Only GPT-5 measured
LMArena Vision: creative writingNot measured1210Only GPT-5 measured
MultiChallengeNot measured63.2%Only GPT-5 measured
Neither model has a result on the other 14 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-4o (2024-08-06) and GPT-5
BenchmarkGPT-4o (2024-08-06)GPT-5Leader
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-4o (2024-08-06)$0.0075Fits in one request
GPT-5$0.0063Fits in one request

GPT-5 costs less

Repository review

50K input + 3K output tokens

GPT-4o (2024-08-06)$0.155Fits in one request
GPT-5$0.092Fits in one request

GPT-5 costs less

Agent loop

200K input + 10K output tokens

GPT-4o (2024-08-06)$0.600Exceeds the context window
GPT-5$0.350Fits in one request

GPT-5 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-4o (2024-08-06) and GPT-5
SpecificationOpenAI GPT-4o (2024-08-06)OpenAI GPT-5
MakerOpenAIOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedAugust 6, 2024August 7, 2025
Context window128K400K
Input $/Mtok$2.50$1.25
Output $/Mtok$10.00$10.00
Coding indexNot benchmarked38.8
Independent measurements behind it03
Cost per solved taskNot computable$0.39
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-4o (2024-08-06) better than GPT-5 for coding?

Only GPT-5 has a coding score, 38.8 on the Vibe Coding Index; GPT-4o (2024-08-06) has none, so the two cannot be ranked on coding. Compare them on price, context and the boards below.

Which is cheaper, GPT-4o (2024-08-06) or GPT-5?

GPT-4o (2024-08-06) costs $2.50 per million input tokens and $10.00 per million output tokens; GPT-5 costs $1.25 and $10.00. Cost per solved task is known for GPT-5 only.

Which has the bigger context window, GPT-4o (2024-08-06) or GPT-5?

GPT-5, with 400K tokens against 128K.

How many benchmarks is the GPT-4o (2024-08-06) vs GPT-5 comparison based on?

56 benchmarks have a result for both models as of October 22, 2026. GPT-4o (2024-08-06)'s coding index rests on 0 independent benchmarks and GPT-5's on 3. Where only one model has a result, the page says so instead of naming a winner.

Compare next