llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeModelsGPT-4

OpenAI model product

GPT-4

GPT-4 is a large multimodal model capable of processing both image and text inputs and generating human-like text outputs. It demonstrates human-level performance on various professional and academic benchmarks.

Updated Aug 10, 2026. Default version: GPT-4

Compare
LLMBoard score28.5GPT-4
Coverage80%8 benchmark families
Context window8.2KTokens
Official input price$30OpenAI API

On this page

  • Specification
  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Versions
  • About
  • Compare
  • Similar models
  • FAQ

Model specification

Structured fields from the published default version.

Version
GPT-4
Released
Jun 13, 2023
Knowledge cutoff
Dec 31, 2022
Parameters
N/A
Context window
8.2K
Max output
8.2K
Inputs
image, text
Outputs
text
Open weights
No
License
Proprietary

Capability profile

This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.

GPT-4 category scores

Benchmark results

Published benchmark records for the scored version GPT-4.

12 rows
Columns

Show columns

AI2 Reasoning Challenge (ARC)1.011100.0%CAug 7, 2026
LSAT0.911100.0%CAug 7, 2026
SAT Math0.911100.0%CAug 7, 2026
Uniform Bar Exam0.911100.0%CAug 7, 2026
Winogrande0.9122100.0%CAug 7, 2026
HellaSwag1.022796.2%CAug 7, 2026
DROP0.8113065.5%CAug 7, 2026
MGSM0.7213133.3%CAug 7, 2026
MMLU0.93010070.7%CAug 7, 2026
HumanEval0.7667613.3%CAug 7, 2026
MATH0.466717.1%CAug 7, 2026
GPQA0.42132338.6%CAug 7, 2026

Arena results

Preference and agent-evaluation signals from published Arena datasets.

58 rows
Columns

Show columns

text style controlpolish1811315.8179N/AAug 6, 2026
text style controljapanese2021201.41,241N/AAug 6, 2026
textpolish2051218.2179N/AAug 6, 2026
textjapanese2161114.61,241N/AAug 6, 2026
text style controlfrench2251269.61,545N/AAug 6, 2026
text style controlspanish2281264.01,364N/AAug 6, 2026
text style controlgerman2311252.62,215N/AAug 6, 2026
text style controlkorean2331177.01,154N/AAug 6, 2026
textfrench2341168.71,545N/AAug 6, 2026
textkorean2361060.01,154N/AAug 6, 2026
textspanish2381167.31,364N/AAug 6, 2026
textgerman2471161.42,215N/AAug 6, 2026
text style controlindustry entertainment and sports and media2481268.613,910N/AAug 6, 2026
text style controlmath2481276.011,181N/AAug 6, 2026
text style controlindustry writing and literature and language2501284.022,099N/AAug 6, 2026
text style controlcreative writing2521265.713,932N/AAug 6, 2026
text style controlindustry mathematical2561271.09,862N/AAug 6, 2026
text style controlinstruction following2611275.529,706N/AAug 6, 2026
text style controlhard prompts2651288.323,040N/AAug 6, 2026
text style controlcoding2661313.913,719N/AAug 6, 2026
text style controlhard prompts english2661301.016,244N/AAug 6, 2026
textmath2701217.011,181N/AAug 6, 2026
text style controlexpert2701250.73,617N/AAug 6, 2026
text style controlenglish2721292.757,478N/AAug 6, 2026
text style controlmulti turn2731261.213,168N/AAug 6, 2026
textindustry mathematical2741201.19,862N/AAug 6, 2026
text style controllonger query2741278.47,523N/AAug 6, 2026
text style controlrussian2741256.05,975N/AAug 6, 2026
text style controloverall2761275.388,723N/AAug 6, 2026
text style controlnon english2761250.231,245N/AAug 6, 2026
text style controlexclude ties2781185.960,653N/AAug 6, 2026
text style controlindustry medicine and healthcare2781263.44,768N/AAug 6, 2026
textindustry writing and literature and language2791214.022,099N/AAug 6, 2026
textcreative writing2811191.813,932N/AAug 6, 2026
textindustry entertainment and sports and media2811180.513,910N/AAug 6, 2026
text style controlchinese2811257.28,540N/AAug 6, 2026
text style controlindustry software and it services2811285.823,796N/AAug 6, 2026
textinstruction following2841189.029,706N/AAug 6, 2026
text style controlindustry legal and government2841272.44,695N/AAug 6, 2026
text style controlindustry life and physical and social science2871275.715,252N/AAug 6, 2026
textmulti turn2881184.713,168N/AAug 6, 2026
textrussian2891172.35,975N/AAug 6, 2026
textcoding2901187.913,719N/AAug 6, 2026
textexpert2901127.23,617N/AAug 6, 2026
texthard prompts2911174.723,040N/AAug 6, 2026
texthard prompts english2911190.016,244N/AAug 6, 2026
text style controlindustry business and management and financial operations2911231.58,676N/AAug 6, 2026
textlonger query2931188.17,523N/AAug 6, 2026
textexclude ties2941058.960,653N/AAug 6, 2026
textnon english2951160.331,245N/AAug 6, 2026
textchinese2961135.28,540N/AAug 6, 2026
textoverall2971186.288,723N/AAug 6, 2026
textenglish2971205.557,478N/AAug 6, 2026
textindustry medicine and healthcare2981122.54,768N/AAug 6, 2026
textindustry legal and government2991154.64,695N/AAug 6, 2026
textindustry software and it services3011169.723,796N/AAug 6, 2026
textindustry business and management and financial operations3081121.58,676N/AAug 6, 2026
textindustry life and physical and social science3091153.815,252N/AAug 6, 2026

Pricing

Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.

Official API
$30 input, $60 output per 1M
Official provider
OpenAI
Lowest third-party
N/A
Tracked offerings
1
1 rows
Columns

Show columns

OpenAIgpt-4global$30$608.2KAug 7, 2026

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

GPT-4 versions

All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.

1 rows
Columns

Show columns

GPT-4Jun 13, 202328.5N/A8.2K8.2KNoProprietary

What is GPT-4?

A concise description based on the published model registry.

GPT-4 is a large multimodal model capable of processing both image and text inputs and generating human-like text outputs. It demonstrates human-level performance on various professional and academic benchmarks.

Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.

Data snapshot: 2026-08-07. Editorial model content is not available in the backend.

GPT-4 vs nearby models

Open a comparison with the three ranked models immediately above and below this model.

GPT-4vsGemini 2.5 Flash LiteGPT-4vsGemma 2 9BGPT-4vsLlama 3.1 8BGPT-4vsGPT-4.1GPT-4vsQwen3.5 4BGPT-4vsGPT-4o

Models similar to GPT-4

Recommendations prioritize the same model type and family, then the closest published LLMBoard score.

#139-0.1
OP

GPT-4.1

OpenAI

28.4 LLMBoard

DetailsCompare
#141-0.6
OP

GPT-4o

OpenAI

27.9 LLMBoard

DetailsCompare
#149-6.0
OP

GPT-4.1-mini

OpenAI

22.5 LLMBoard

DetailsCompare
#109+13.0
OP

GPT-4o-mini

OpenAI

41.5 LLMBoard

DetailsCompare
#105+14.2
OP

GPT-5.4-nano

OpenAI

42.8 LLMBoard

DetailsCompare
#163-16.1
OP

GPT-3.5-Turbo

OpenAI

12.5 LLMBoard

DetailsCompare

FAQ

Common questions about GPT-4.

When was GPT-4 released?

GPT-4's default version was released on Jun 13, 2023.

How much does GPT-4 cost?

GPT-4's official API price is $30 per million input tokens and $60 per million output tokens via OpenAI.

Who created GPT-4?

GPT-4 is published under OpenAI in the model registry.

What is the context window for GPT-4?

The default version has a 8.2K token context window.

Is GPT-4 open weight?

No. The default version is not marked as having publicly available weights.

How many API providers offer GPT-4?

1 published provider offerings are linked to the default version.

What models should I compare GPT-4 with?

Nearby ranked alternatives include Gemini 2.5 Flash Lite, Gemma 2 9B, Llama 3.1 8B.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai