LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

GPT-4 vs GPT-5 Nano

Updated October 21, 2026. 35 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace GPT-4 Replace GPT-5 Nano
GPT-4OpenAI
Coding
22.4
Overall
6.7
Output $/M
$60.00
1
GPT-5 NanoOpenAI
Coding
34.8
Overall
13.0
Output $/M
$0.40
33
vs boards won of 35 shared, 1 tied

Decision reading

Pick GPT-5 Nano for coding: it scores 34.8 on the Vibe Coding Index against 22.4 for GPT-4.

Pick GPT-4 when the benchmark that matters is LMCA, where it leads.

Model AGPT-4OpenAI22.4/1001 independent benchmarkNo cost per solved taskModel BGPT-5 NanoOpenAI34.8/1001 independent benchmark$0.109 per solved task
Shared results
35
GPT-4 only
10
GPT-5 Nano only
50
Like-for-like categories
6 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-4 22.4 from 1 benchmark, GPT-5 Nano 34.8 from 1 benchmark.
Widest category
Reasoning, 26.1 points apart on average over 4 shared benchmarks.
Widest single gap
IFBench: GPT-4 33.2% against GPT-5 Nano 67.6%, 34.4 points apart on a 0 to 100 scale.
Output price
GPT-4 $60.00 against GPT-5 Nano $0.40 per million output tokens, 150.0x apart.
Context window
GPT-4 takes 8K tokens, GPT-5 Nano 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 NanoTies
Coding03
Intelligence02
Reasoning04
Math02
Knowledge05
General1171 tie
All shared boards1331 tie
CodingLike-for-likeFour of these boards feed the Vibe Coding Index03
Coding benchmarks for GPT-4 and GPT-5 Nano
BenchmarkGPT-4GPT-5 NanoLeader
SWE-bench Verified22.4%34.8%GPT-5 Nano
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
LiveCodeBench (Vals AI)Not measured70.2%Only GPT-5 Nano measured
LiveCodeBench (Artificial Analysis run)Not measured78.9%Only GPT-5 Nano measured
Terminal-Bench Hard (Artificial Analysis run)Not measured17.4%Only GPT-5 Nano measured
Terminal-BenchNot measured21.8%Only GPT-5 Nano measured
WeirdMLNot measured38.1%Only GPT-5 Nano measured
LMArena Text: coding12091351GPT-5 Nano
LMArena Text: software and IT11951345GPT-5 Nano
Neither model has a result on the other 27 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for GPT-4 and GPT-5 Nano
BenchmarkGPT-4GPT-5 NanoLeader
AA Intelligence Index6.713.0GPT-5 Nano
Epoch Capabilities Index125.7139.2GPT-5 Nano
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
Agentic work benchmarks for GPT-4 and GPT-5 Nano
BenchmarkGPT-4GPT-5 NanoLeader
τ²-Bench TelecomNot measured36.5%Only GPT-5 Nano measured
Neither model has a result on the other 38 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index04
Reasoning benchmarks for GPT-4 and GPT-5 Nano
BenchmarkGPT-4GPT-5 NanoLeader
GPQA DiamondNot measured63.4%Only GPT-5 Nano measured
MMMU Pro (Vals AI)Not measured70.9%Only GPT-5 Nano measured
GPQA Diamond (Artificial Analysis run)34.9%67.6%GPT-5 Nano
Humanity's Last Exam (Artificial Analysis run)Not measured9.5%Only GPT-5 Nano measured
GPQA Diamond (Epoch AI run)Not measured69.4%Only GPT-5 Nano measured
ARC-AGINot measured20.7%Only GPT-5 Nano measured
ARC-AGI-2Not measured2.6%Only GPT-5 Nano measured
Chess puzzlesNot measured22.0%Only GPT-5 Nano measured
Mystery game puzzlesNot measured9.0%Only GPT-5 Nano measured
VPCTNot measured37.2%Only GPT-5 Nano measured
BIG-Bench Hard75.1%Not measuredOnly GPT-4 measured
LMArena Text: hard prompts12001328GPT-5 Nano
LMArena Text: expert11491321GPT-5 Nano
LMArena Text: hard prompts in English12091338GPT-5 Nano
LMArena Vision: diagramsNot measured1141Only GPT-5 Nano measured
LMArena Vision: homeworkNot measured1157Only GPT-5 Nano measured
Neither model has a result on the other 5 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for GPT-4 and GPT-5 Nano
BenchmarkGPT-4GPT-5 NanoLeader
AIMENot measured81.2%Only GPT-5 Nano measured
MATH 500 (Vals AI)Not measured93.8%Only GPT-5 Nano measured
MGSM (Vals AI)Not measured89.3%Only GPT-5 Nano measured
AA Math IndexNot measured83.7Only GPT-5 Nano measured
AIME 2025 (Artificial Analysis run)Not measured83.7%Only GPT-5 Nano measured
OTIS Mock AIMENot measured81.1%Only GPT-5 Nano measured
FrontierMath, tiers 1 to 3Not measured20.0%Only GPT-5 Nano measured
FrontierMath, tier 4Not measured2.4%Only GPT-5 Nano measured
ProofBenchNot measured12.0%Only GPT-5 Nano measured
MATH level 5Not measured95.2%Only GPT-5 Nano measured
GSM8K92.0%Not measuredOnly GPT-4 measured
LMArena Text: math12301317GPT-5 Nano
LMArena Text: mathematical work12281326GPT-5 Nano
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index05
Knowledge benchmarks for GPT-4 and GPT-5 Nano
BenchmarkGPT-4GPT-5 NanoLeader
MMLU ProNot measured76.1%Only GPT-5 Nano measured
LegalBench (Vals AI)Not measured50.1%Only GPT-5 Nano measured
CaseLaw (Vals AI)Not measured52.6%Only GPT-5 Nano measured
TaxEval (Vals AI)Not measured67.4%Only GPT-5 Nano measured
MortgageTax (Vals AI)Not measured53.6%Only GPT-5 Nano measured
MedQA (Vals AI)Not measured93.3%Only GPT-5 Nano measured
MedCode (Vals AI)Not measured30.4%Only GPT-5 Nano measured
MMLU Pro (Artificial Analysis run)56.2%78.0%GPT-5 Nano
SimpleQA VerifiedNot measured11.7%Only GPT-5 Nano measured
MMLU86.4%Not measuredOnly GPT-4 measured
AI2 Reasoning Challenge96.3%Not measuredOnly GPT-4 measured
LMArena Text: science11771318GPT-5 Nano
LMArena Text: medicine and healthcare11451335GPT-5 Nano
LMArena Text: legal and government11911298GPT-5 Nano
LMArena Text: business and finance11451311GPT-5 Nano
Neither model has a result on the other 2 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
Web design benchmarks for GPT-4 and GPT-5 Nano
BenchmarkGPT-4GPT-5 NanoLeader
Design Arena: websitesNot measured1101Only GPT-5 Nano measured
Design Arena: UI componentsNot measured1066Only GPT-5 Nano measured
Design Arena: game devNot measured1045Only GPT-5 Nano measured
Design Arena: data vizNot measured1056Only GPT-5 Nano measured
Design Arena: 3DNot measured966Only GPT-5 Nano measured
Design Arena: all code categoriesNot measured1084Only GPT-5 Nano measured
Neither model has a result on the other 3 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index117
General benchmarks for GPT-4 and GPT-5 Nano
BenchmarkGPT-4GPT-5 NanoLeader
SAGE (Vals AI)Not measured30.4%Only GPT-5 Nano measured
MedScribe (Vals AI)Not measured72.9%Only GPT-5 Nano measured
IFBench33.2%67.6%GPT-5 Nano
Long context reasoning (AA-LCR)Not measured45.0%Only GPT-5 Nano measured
DTBench62.7%62.7%Tie
LMCA17.1%7.9%GPT-4
Fiction.LiveBenchNot measured44.4%Only GPT-5 Nano measured
HellaSwag95.3%Not measuredOnly GPT-4 measured
WinoGrande87.5%Not measuredOnly GPT-4 measured
LMArena Text12061320GPT-5 Nano
LMArena Text: instruction following12011306GPT-5 Nano
LMArena Text: creative writing11911249GPT-5 Nano
LMArena VisionNot measured1159Only GPT-5 Nano measured
LMArena Text: English12201321GPT-5 Nano
LMArena Text: non-English11941313GPT-5 Nano
LMArena Text: Chinese11841356GPT-5 Nano
LMArena Text: German11981327GPT-5 Nano
LMArena Text: Japanese11371227GPT-5 Nano
LMArena Text: Korean10871269GPT-5 Nano
LMArena Text: French1220Not measuredOnly GPT-4 measured
LMArena Text: Spanish11971360GPT-5 Nano
LMArena Text: Russian11951296GPT-5 Nano
LMArena Text: Polish12651314GPT-5 Nano
LMArena Text: multi-turn12061311GPT-5 Nano
LMArena Text: longer queries11901312GPT-5 Nano
LMArena Text: writing and language12191283GPT-5 Nano
LMArena Text: entertainment and media11841268GPT-5 Nano
LMArena Vision: EnglishNot measured1170Only GPT-5 Nano measured
LMArena Vision: ChineseNot measured1176Only GPT-5 Nano measured
LMArena Vision: reading textNot measured1152Only GPT-5 Nano measured
LMArena Vision: humorNot measured1110Only GPT-5 Nano measured
Neither model has a result on the other 15 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 Nano
BenchmarkGPT-4GPT-5 NanoLeader
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 Nano$0.0003Fits in one request

GPT-5 Nano costs less

Repository review

50K input + 3K output tokens

GPT-4$1.68Exceeds the context window
GPT-5 Nano$0.0037Fits in one request

GPT-5 Nano costs less

Agent loop

200K input + 10K output tokens

GPT-4$6.60Exceeds the context window
GPT-5 Nano$0.014Fits in one request

GPT-5 Nano 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 Nano
SpecificationOpenAI GPT-4OpenAI GPT-5 Nano
MakerOpenAIOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedMay 28, 2023August 7, 2025
Context window8K400K
Input $/Mtok$30.00$0.05
Output $/Mtok$60.00$0.40
Coding index22.434.8
Independent measurements behind it11
Cost per solved taskNot computable$0.109
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-4 better than GPT-5 Nano for coding?

Pick GPT-5 Nano for coding: it scores 34.8 on the Vibe Coding Index against 22.4 for GPT-4. Pick GPT-4 when the benchmark that matters is LMCA, where it leads.

Which is cheaper, GPT-4 or GPT-5 Nano?

GPT-4 costs $30.00 per million input tokens and $60.00 per million output tokens; GPT-5 Nano costs $0.05 and $0.40. Cost per solved task is known for GPT-5 Nano only.

Which has the bigger context window, GPT-4 or GPT-5 Nano?

GPT-5 Nano, with 400K tokens against 8K.

How many benchmarks is the GPT-4 vs GPT-5 Nano comparison based on?

35 benchmarks have a result for both models as of October 21, 2026. GPT-4's coding index rests on 1 independent benchmark and GPT-5 Nano's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next