LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

GPT-4o (2024-11-20) vs GPT-5.3-Codex

Updated October 21, 2026. 3 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace GPT-4o (2024-11-20) Replace GPT-5.3-Codex
GPT-4o (2024-11-20)OpenAI
Coding
18.2
Overall
8.4
Output $/M
$10.00
0
GPT-5.3-CodexOpenAI
Coding
29.5
Overall
32.5
Output $/M
$14.00
3
vs boards won of 3 shared

Decision reading

Pick GPT-5.3-Codex for coding: it scores 29.5 on the Vibe Coding Index against 18.2 for GPT-4o (2024-11-20).

Pick GPT-4o (2024-11-20) when output tokens cost 1.4x less.

Model AGPT-4o (2024-11-20)OpenAI18.2/1001 independent benchmarkNo cost per solved taskModel BGPT-5.3-CodexOpenAI29.5/1001 independent benchmark$0.59 per solved task
Shared results
3
GPT-4o (2024-11-20) only
21
GPT-5.3-Codex only
31
Like-for-like categories
2 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

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 (2024-11-20) 18.2 from 1 benchmark, GPT-5.3-Codex 29.5 from 1 benchmark.
Widest category
Coding, 49.0 points apart on average over 2 shared benchmarks.
Widest single gap
WeirdML: GPT-4o (2024-11-20) 25.1% against GPT-5.3-Codex 79.3%, 54.2 points apart on a 0 to 100 scale.
Output price
GPT-4o (2024-11-20) $10.00 against GPT-5.3-Codex $14.00 per million output tokens, 1.4x apart.
Context window
GPT-4o (2024-11-20) takes 128K tokens, GPT-5.3-Codex 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 (2024-11-20)BarsGPT-5.3-CodexTies
Coding02
Intelligence01
All shared boards03
CodingLike-for-likeFour of these boards feed the Vibe Coding Index02
Coding benchmarks for GPT-4o (2024-11-20) and GPT-5.3-Codex
BenchmarkGPT-4o (2024-11-20)GPT-5.3-CodexLeader
Aider polyglot18.2%Not measuredOnly GPT-4o (2024-11-20) measured
LMArena WebDevNot measured1407Only GPT-5.3-Codex measured
LiveCodeBench (Vals AI)43.4%87.3%GPT-5.3-Codex
SWE-bench Verified (Vals AI)Not measured78.0%Only GPT-5.3-Codex measured
Vibe Code Bench (Vals AI)Not measured61.8%Only GPT-5.3-Codex measured
IOI (Vals AI)Not measured53.8%Only GPT-5.3-Codex measured
Terminal-Bench Hard (Artificial Analysis run)Not measured53.0%Only GPT-5.3-Codex measured
Terminal-BenchNot measured78.4%Only GPT-5.3-Codex measured
GSO-Bench0.0%Not measuredOnly GPT-4o (2024-11-20) measured
WeirdML25.1%79.3%GPT-5.3-Codex
Cybench12.5%Not measuredOnly GPT-4o (2024-11-20) measured
ALE-BenchNot measured1655.2Only GPT-5.3-Codex measured
LMArena WebDev: ReactNot measured1395Only GPT-5.3-Codex measured
LMArena WebDev: HTMLNot measured1422Only GPT-5.3-Codex measured
LMArena WebDev: from an imageNot measured1443Only GPT-5.3-Codex measured
Neither model has a result on the other 23 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for GPT-4o (2024-11-20) and GPT-5.3-Codex
BenchmarkGPT-4o (2024-11-20)GPT-5.3-CodexLeader
AA Intelligence Index8.432.5GPT-5.3-Codex
Epoch Capabilities IndexNot measured157.1Only GPT-5.3-Codex measured
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
Agentic work benchmarks for GPT-4o (2024-11-20) and GPT-5.3-Codex
BenchmarkGPT-4o (2024-11-20)GPT-5.3-CodexLeader
Design Arena: agents building web appsNot measured1033Only GPT-5.3-Codex measured
Design Arena: agents building full-stack appsNot measured983Only GPT-5.3-Codex measured
Design Arena: agents building mobile appsNot measured1054Only GPT-5.3-Codex measured
Design Arena: agents building Android appsNot measured1084Only GPT-5.3-Codex measured
Design Arena: agents building Godot gamesNot measured1124Only GPT-5.3-Codex measured
τ²-Bench TelecomNot measured86.0%Only GPT-5.3-Codex measured
METR time horizonsNot measured74.5%Only GPT-5.3-Codex measured
TheAgentCompany8.6%Not measuredOnly GPT-4o (2024-11-20) measured
Vending-Bench 2Not measured$5,940Only GPT-5.3-Codex measured
Neither model has a result on the other 30 boards here
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
Reasoning benchmarks for GPT-4o (2024-11-20) and GPT-5.3-Codex
BenchmarkGPT-4o (2024-11-20)GPT-5.3-CodexLeader
GPQA Diamond53.8%Not measuredOnly GPT-4o (2024-11-20) measured
MMMU Pro (Vals AI)62.2%Not measuredOnly GPT-4o (2024-11-20) measured
GPQA Diamond (Artificial Analysis run)Not measured91.5%Only GPT-5.3-Codex measured
Humanity's Last Exam (Artificial Analysis run)Not measured42.5%Only GPT-5.3-Codex measured
GPQA Diamond (Epoch AI run)47.9%Not measuredOnly GPT-4o (2024-11-20) measured
VPCT40.0%Not measuredOnly GPT-4o (2024-11-20) measured
Neither model has a result on the other 15 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
Math benchmarks for GPT-4o (2024-11-20) and GPT-5.3-Codex
BenchmarkGPT-4o (2024-11-20)GPT-5.3-CodexLeader
AIME11.9%Not measuredOnly GPT-4o (2024-11-20) measured
MATH 500 (Vals AI)74.0%Not measuredOnly GPT-4o (2024-11-20) measured
MGSM (Vals AI)90.4%Not measuredOnly GPT-4o (2024-11-20) measured
OTIS Mock AIME6.3%Not measuredOnly GPT-4o (2024-11-20) measured
MATH level 549.8%Not measuredOnly GPT-4o (2024-11-20) measured
Neither model has a result on the other 8 boards here
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Knowledge benchmarks for GPT-4o (2024-11-20) and GPT-5.3-Codex
BenchmarkGPT-4o (2024-11-20)GPT-5.3-CodexLeader
MMLU Pro72.6%Not measuredOnly GPT-4o (2024-11-20) measured
LegalBench (Vals AI)82.2%Not measuredOnly GPT-4o (2024-11-20) measured
CaseLaw (Vals AI)59.7%Not measuredOnly GPT-4o (2024-11-20) measured
CorpFin (Vals AI)45.9%Not measuredOnly GPT-4o (2024-11-20) measured
TaxEval (Vals AI)74.5%Not measuredOnly GPT-4o (2024-11-20) measured
MortgageTax (Vals AI)57.4%Not measuredOnly GPT-4o (2024-11-20) measured
GeoBench71.0%Not measuredOnly GPT-4o (2024-11-20) measured
Neither model has a result on the other 10 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for GPT-4o (2024-11-20) and GPT-5.3-Codex
BenchmarkGPT-4o (2024-11-20)GPT-5.3-CodexLeader
Design Arena: websitesNot measured1163Only GPT-5.3-Codex measured
Design Arena: UI componentsNot measured1137Only GPT-5.3-Codex measured
Design Arena: game devNot measured1162Only GPT-5.3-Codex measured
Design Arena: data vizNot measured1164Only GPT-5.3-Codex measured
Design Arena: 3DNot measured1008Only GPT-5.3-Codex measured
Design Arena: all code categoriesNot measured1145Only GPT-5.3-Codex measured
Design Arena: SVGNot measured1129Only GPT-5.3-Codex measured
Design Arena: ASCII artNot measured1151Only GPT-5.3-Codex measured
Neither model has a result on the other 1 board here
GeneralDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
General benchmarks for GPT-4o (2024-11-20) and GPT-5.3-Codex
BenchmarkGPT-4o (2024-11-20)GPT-5.3-CodexLeader
IFBenchNot measured75.4%Only GPT-5.3-Codex measured
Long context reasoning (AA-LCR)Not measured83.3%Only GPT-5.3-Codex measured
Creative writing (Lech Mazur)81.8%Not measuredOnly GPT-4o (2024-11-20) measured
Neither model has a result on the other 43 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-4o (2024-11-20) and GPT-5.3-Codex
BenchmarkGPT-4o (2024-11-20)GPT-5.3-CodexLeader
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 (2024-11-20)$0.0075Fits in one request
GPT-5.3-Codex$0.0088Fits in one request

GPT-4o (2024-11-20) costs less

Repository review

50K input + 3K output tokens

GPT-4o (2024-11-20)$0.155Fits in one request
GPT-5.3-Codex$0.130Fits in one request

GPT-5.3-Codex costs less

Agent loop

200K input + 10K output tokens

GPT-4o (2024-11-20)$0.600Exceeds the context window
GPT-5.3-Codex$0.490Fits in one request

GPT-5.3-Codex 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 (2024-11-20) and GPT-5.3-Codex
SpecificationOpenAI GPT-4o (2024-11-20)OpenAI GPT-5.3-Codex
MakerOpenAIOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedNovember 20, 2024February 24, 2026
Context window128K400K
Input $/Mtok$2.50$1.75
Output $/Mtok$10.00$14.00
Coding index18.229.5
Independent measurements behind it11
Cost per solved taskNot computable$0.59
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-4o (2024-11-20) better than GPT-5.3-Codex for coding?

Pick GPT-5.3-Codex for coding: it scores 29.5 on the Vibe Coding Index against 18.2 for GPT-4o (2024-11-20). Pick GPT-4o (2024-11-20) when output tokens cost 1.4x less.

Which is cheaper, GPT-4o (2024-11-20) or GPT-5.3-Codex?

GPT-4o (2024-11-20) costs $2.50 per million input tokens and $10.00 per million output tokens; GPT-5.3-Codex costs $1.75 and $14.00. Cost per solved task is known for GPT-5.3-Codex only.

Which has the bigger context window, GPT-4o (2024-11-20) or GPT-5.3-Codex?

GPT-5.3-Codex, with 400K tokens against 128K.

How many benchmarks is the GPT-4o (2024-11-20) vs GPT-5.3-Codex comparison based on?

3 benchmarks have a result for both models as of October 21, 2026. GPT-4o (2024-11-20)'s coding index rests on 1 independent benchmark and GPT-5.3-Codex's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next