Enter opens the highlighted result. Esc closes.

GPT-4 vs GPT-5.1-Codex

GPT-5.1-Codex leads GPT-4 on the Artificial Analysis Intelligence Index, 23.7 to 6.7, and GPT-5.1-Codex costs 6.0x less per output token ($10.00 vs $60.00 per million). Updated October 21, 2026; 5 benchmarks have a result for both.

Replace GPT-4 Replace GPT-5.1-Codex
GPT-4OpenAI
Coding
No data
Overall
No data
Output $/M
$60.00
0
GPT-5.1-CodexOpenAI
Coding
15.3
Overall
No data
Output $/M
$10.00
5
vs boards won of 5 shared

GPT-4 or GPT-5.1-Codex: which to pick

Only GPT-5.1-Codex has a coding score, 15.3 on the Vibe Coding Index; GPT-4 has none, so the two cannot be ranked on coding.

Compare them on price, context and the boards below.

Model AGPT-4OpenAINot benchmarkedNo coding benchmarkNo cost per solved taskModel BGPT-5.1-CodexOpenAI15.3/1002 independent benchmarks$0.892 per solved task
Shared results
5
GPT-4 only
40
GPT-5.1-Codex only
21
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-5.1-Codex 15.3 from 2 benchmarks.
Widest category
Reasoning, 51.1 points apart on average over 1 shared benchmark.
Widest single gap
GPQA Diamond (Artificial Analysis run): GPT-4 34.9% against GPT-5.1-Codex 86.0%, 51.1 points apart on a 0 to 100 scale.
Output price
GPT-4 $60.00 against GPT-5.1-Codex $10.00 per million output tokens, 6.0x apart.
Context window
GPT-4 takes 8K tokens, GPT-5.1-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-4BarsGPT-5.1-CodexTies
Coding01
Intelligence01
Reasoning01
Knowledge01
General01
All shared boards05
CodingLike-for-likeSix of these boards feed the Vibe Coding Index01
Coding benchmarks for GPT-4 and GPT-5.1-Codex
BenchmarkGPT-4GPT-5.1-CodexLeader
SWE-bench Verified22.4%66.0%GPT-5.1-Codex
SWE-bench Lite39.7%Not measuredOnly GPT-4 measured
SWE-bench (full test set)12.5%Not measuredOnly GPT-4 measured
LMArena WebDevNot measured1337Only GPT-5.1-Codex measured
AA Coding Index13.1Not measuredOnly GPT-4 measured
LiveCodeBench (Vals AI)Not measured85.5%Only GPT-5.1-Codex measured
Vibe Code Bench (Vals AI)Not measured13.1%Only GPT-5.1-Codex measured
LiveCodeBench (Artificial Analysis run)Not measured84.9%Only GPT-5.1-Codex measured
Terminal-Bench Hard (Artificial Analysis run)Not measured34.8%Only GPT-5.1-Codex measured
Terminal-BenchNot measured57.8%Only GPT-5.1-Codex measured
ALE-BenchNot measured1244.9Only GPT-5.1-Codex measured
LMArena Text: coding1209Not measuredOnly GPT-4 measured
LMArena Text: software and IT1195Not measuredOnly GPT-4 measured
LMArena WebDev: HTMLNot measured1346Only GPT-5.1-Codex 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-4 and GPT-5.1-Codex
BenchmarkGPT-4GPT-5.1-CodexLeader
AA Intelligence Index6.723.7GPT-5.1-Codex
Epoch Capabilities Index125.7Not measuredOnly GPT-4 measured
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
Agentic work benchmarks for GPT-4 and GPT-5.1-Codex
BenchmarkGPT-4GPT-5.1-CodexLeader
Design Arena: agents building web appsNot measured1018Only GPT-5.1-Codex measured
Design Arena: agents building full-stack appsNot measured1086Only GPT-5.1-Codex measured
Design Arena: agents building mobile appsNot measured1191Only GPT-5.1-Codex measured
τ²-Bench TelecomNot measured83.0%Only GPT-5.1-Codex measured
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index01
Reasoning benchmarks for GPT-4 and GPT-5.1-Codex
BenchmarkGPT-4GPT-5.1-CodexLeader
GPQA Diamond (Artificial Analysis run)34.9%86.0%GPT-5.1-Codex
Humanity's Last Exam (Artificial Analysis run)Not measured25.7%Only GPT-5.1-Codex measured
BIG-Bench Hard75.1%Not measuredOnly GPT-4 measured
LMArena Text: hard prompts1200Not measuredOnly GPT-4 measured
LMArena Text: expert1149Not measuredOnly GPT-4 measured
LMArena Text: hard prompts in English1209Not measuredOnly GPT-4 measured
Neither model has a result on the other 16 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
Math benchmarks for GPT-4 and GPT-5.1-Codex
BenchmarkGPT-4GPT-5.1-CodexLeader
AA Math IndexNot measured95.7Only GPT-5.1-Codex measured
AIME 2025 (Artificial Analysis run)Not measured95.7%Only GPT-5.1-Codex measured
GSM8K92.0%Not measuredOnly GPT-4 measured
LMArena Text: math1230Not measuredOnly GPT-4 measured
LMArena Text: mathematical work1228Not measuredOnly GPT-4 measured
Neither model has a result on the other 8 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index01
Knowledge benchmarks for GPT-4 and GPT-5.1-Codex
BenchmarkGPT-4GPT-5.1-CodexLeader
MMLU Pro (Artificial Analysis run)56.2%86.0%GPT-5.1-Codex
MMLU86.4%Not measuredOnly GPT-4 measured
AI2 Reasoning Challenge96.3%Not measuredOnly GPT-4 measured
LMArena Text: science1177Not measuredOnly GPT-4 measured
LMArena Text: medicine and healthcare1145Not measuredOnly GPT-4 measured
LMArena Text: legal and government1191Not measuredOnly GPT-4 measured
LMArena Text: business and finance1145Not measuredOnly GPT-4 measured
Neither model has a result on the other 11 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
Web design benchmarks for GPT-4 and GPT-5.1-Codex
BenchmarkGPT-4GPT-5.1-CodexLeader
Design Arena: websitesNot measured1162Only GPT-5.1-Codex measured
Design Arena: UI componentsNot measured1237Only GPT-5.1-Codex measured
Design Arena: game devNot measured1138Only GPT-5.1-Codex measured
Design Arena: data vizNot measured1213Only GPT-5.1-Codex measured
Design Arena: all code categoriesNot measured1152Only GPT-5.1-Codex measured
Neither model has a result on the other 4 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index01
General benchmarks for GPT-4 and GPT-5.1-Codex
BenchmarkGPT-4GPT-5.1-CodexLeader
IFBench33.2%70.0%GPT-5.1-Codex
Long context reasoning (AA-LCR)Not measured69.3%Only GPT-5.1-Codex 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 Text1206Not measuredOnly GPT-4 measured
LMArena Text: instruction following1201Not measuredOnly GPT-4 measured
LMArena Text: creative writing1191Not measuredOnly GPT-4 measured
LMArena Text: English1220Not measuredOnly GPT-4 measured
LMArena Text: non-English1194Not measuredOnly GPT-4 measured
LMArena Text: Chinese1184Not measuredOnly GPT-4 measured
LMArena Text: German1198Not measuredOnly GPT-4 measured
LMArena Text: Japanese1137Not measuredOnly GPT-4 measured
LMArena Text: Korean1087Not measuredOnly GPT-4 measured
LMArena Text: French1220Not measuredOnly GPT-4 measured
LMArena Text: Spanish1197Not measuredOnly GPT-4 measured
LMArena Text: Russian1195Not measuredOnly GPT-4 measured
LMArena Text: Polish1265Not measuredOnly GPT-4 measured
LMArena Text: multi-turn1206Not measuredOnly GPT-4 measured
LMArena Text: longer queries1190Not measuredOnly GPT-4 measured
LMArena Text: writing and language1219Not measuredOnly GPT-4 measured
LMArena Text: entertainment and media1184Not measuredOnly GPT-4 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-5.1-Codex
BenchmarkGPT-4GPT-5.1-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-4$0.060Fits in one request
GPT-5.1-Codex$0.0063Fits in one request

GPT-5.1-Codex costs less

Repository review

50K input + 3K output tokens

GPT-4$1.68Exceeds the context window
GPT-5.1-Codex$0.092Fits in one request

GPT-5.1-Codex costs less

Agent loop

200K input + 10K output tokens

GPT-4$6.60Exceeds the context window
GPT-5.1-Codex$0.350Fits in one request

GPT-5.1-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-4 and GPT-5.1-Codex
SpecificationOpenAI GPT-4OpenAI GPT-5.1-Codex
MakerOpenAIOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedMay 28, 2023November 13, 2025
Context window8K400K
Input $/Mtok$30.00$1.25
Output $/Mtok$60.00$10.00
Coding indexNot benchmarked15.3
Independent measurements behind it02
Cost per solved taskNot computable$0.892
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-4 better than GPT-5.1-Codex for coding?

Only GPT-5.1-Codex has a coding score, 15.3 on the Vibe Coding Index; GPT-4 has none, so the two cannot be ranked on coding. Compare them on price, context and the boards below.

Which is cheaper, GPT-4 or GPT-5.1-Codex?

GPT-4 costs $30.00 per million input tokens and $60.00 per million output tokens; GPT-5.1-Codex costs $1.25 and $10.00. Cost per solved task is known for GPT-5.1-Codex only.

Which has the bigger context window, GPT-4 or GPT-5.1-Codex?

GPT-5.1-Codex, with 400K tokens against 8K.

How many benchmarks is the GPT-4 vs GPT-5.1-Codex comparison based on?

5 benchmarks have a result for both models as of October 21, 2026. GPT-4's coding index rests on 0 independent benchmarks and GPT-5.1-Codex's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next