llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeModelsGPT-4.1

OpenAI model product

GPT-4.1

GPT-4.1 is OpenAI's latest and most advanced flagship model, significantly improving upon GPT-4 Turbo in performance across benchmarks, speed, and cost-effectiveness.

Updated Aug 10, 2026. Default version: GPT-4.1

Compare
LLMBoard score28.4GPT-4.1
Coverage80%13 benchmark families
Context window1MTokens
Official input price$2OpenAI 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-4.1
Released
Apr 14, 2025
Knowledge cutoff
Jun 1, 2024
Parameters
N/A
Context window
1M
Max output
32.8K
Inputs
image, pdf, 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-4.1 category scores

Benchmark results

Published benchmark records for the scored version GPT-4.1.

29 rows
Columns

Show columns

Video-MME (long, no subtitles)0.711100.0%CAug 7, 2026
ComplexFuncBench0.72783.3%CAug 7, 2026
OpenAI-MRCR: 2 needle 1M0.53550.0%CAug 7, 2026
Internal API instruction following (hard)0.54750.0%CAug 7, 2026
OpenAI-MRCR: 2 needle 128k0.64962.5%CAug 7, 2026
Aider-Polyglot Edit0.561044.4%CAug 7, 2026
COLLIE0.761044.4%CAug 7, 2026
CharXiv-D0.981653.3%CAug 7, 2026
MMLU0.9910091.9%CAug 7, 2026
Graphwalks parents <128k0.6111841.2%CAug 7, 2026
MathVista0.7113973.7%CAug 7, 2026
Graphwalks BFS <128k0.6122247.6%CAug 7, 2026
TAU-bench Airline0.5132345.5%CAug 7, 2026
TAU-bench Retail0.7142545.8%CAug 7, 2026
Aider-Polyglot0.5152233.3%CAug 7, 2026
Graphwalks parents >128k0.3151817.6%CAug 7, 2026
Multi-IF0.7152026.3%CAug 7, 2026
Graphwalks BFS >128k0.220229.5%CAug 7, 2026
MMMLU0.9204960.4%CAug 7, 2026
MMMU0.7236364.5%CAug 7, 2026
Multi-Challenge0.4252914.3%CAug 7, 2026
HMMT 20250.333330.0%CAug 7, 2026
IFEval0.9336550.0%CAug 7, 2026
CharXiv-R0.6384719.6%CAug 7, 2026
AIME 20240.548539.6%CAug 7, 2026
SWE-Bench Verified0.58410419.4%CAug 7, 2026
Humanity's Last Exam0.186926.6%CAug 7, 2026
AIME 20250.51061147.1%CAug 7, 2026
GPQA0.714323338.8%CAug 7, 2026

Arena results

Preference and agent-evaluation signals from published Arena datasets.

93 rows
Columns

Show columns

vision style controlcreative writing111233.71,432N/AJan 9, 2026
vision style controlcaptioning131207.4432N/AAug 6, 2026
visioncreative writing161222.91,432N/AJan 9, 2026
visioncaptioning191204.2432N/AAug 6, 2026
visionentity recognition331205.6397N/AAug 6, 2026
vision style controlentity recognition341183.4397N/AAug 6, 2026
vision style controlcreative writing vision461227.71,262N/AAug 6, 2026
vision style controlhomework561248.71,506N/AAug 6, 2026
visionhomework571246.21,506N/AAug 6, 2026
visioncreative writing vision581222.21,262N/AAug 6, 2026
visionhumor581196.11,388N/AAug 6, 2026
vision style controlchinese581239.31,370N/AAug 6, 2026
vision style controlhumor581183.11,388N/AAug 6, 2026
vision style controlocr631226.311,488N/AAug 6, 2026
vision style controloverall641214.041,556N/AAug 6, 2026
visionchinese651229.01,370N/AAug 6, 2026
vision style controldiagram661232.52,794N/AAug 6, 2026
vision style controlenglish671211.019,776N/AAug 6, 2026
visionoverall681210.141,556N/AAug 6, 2026
visiondiagram681215.22,794N/AAug 6, 2026
visionocr681217.611,488N/AAug 6, 2026
visionenglish711212.319,776N/AAug 6, 2026
text style controlpolish761427.52,998N/AAug 6, 2026
text style controlkorean831380.61,005N/AAug 6, 2026
text style controlindustry entertainment and sports and media861399.89,039N/AAug 6, 2026
text style controlcreative writing871402.26,690N/AAug 6, 2026
text style controlindustry legal and government911437.63,276N/AAug 6, 2026
text style controlmulti turn961429.58,951N/AAug 6, 2026
text factualityindustry writing and literature and language981399.7947N/AAug 6, 2026
text factualitymulti turn1001422.4746N/AAug 6, 2026
text style controlindustry writing and literature and language1001403.811,370N/AAug 6, 2026
text style controlgerman1021409.81,234N/AAug 6, 2026
text style controlrussian1081408.83,056N/AAug 6, 2026
text style controlnon english1111402.225,194N/AAug 6, 2026
text style controlindustry business and management and financial operations1121413.98,283N/AAug 6, 2026
text style controlspanish1121403.2984N/AAug 6, 2026
textpolish1141388.82,998N/AAug 6, 2026
text style controllonger query1141424.49,799N/AAug 6, 2026
text style controljapanese1151342.11,017N/AAug 6, 2026
textkorean1171349.31,005N/AAug 6, 2026
text style controlinstruction following1171402.713,272N/AAug 6, 2026
text style controlexclude ties1181401.936,166N/AAug 6, 2026
text factualityinstruction following1191392.11,222N/AAug 6, 2026
text style controloverall1201413.850,899N/AAug 6, 2026
textgerman1211381.31,234N/AAug 6, 2026
text factualitylonger query1211405.61,034N/AAug 6, 2026
textjapanese1221314.51,017N/AAug 6, 2026
text factualityindustry business and management and financial operations1221387.0852N/AAug 6, 2026
text style controlfrench1231419.5688N/AAug 6, 2026
text style controlhard prompts1231430.822,131N/AAug 6, 2026
text factualityenglish1241416.83,326N/AAug 6, 2026
text factualityhard prompts english1241421.91,175N/AAug 6, 2026
text style controlcoding1241456.09,301N/AAug 6, 2026
text style controlhard prompts english1241436.811,884N/AAug 6, 2026
text style controlindustry medicine and healthcare1241432.62,789N/AAug 6, 2026
text factualitycoding1251425.2865N/AAug 6, 2026
text style controlenglish1251421.925,653N/AAug 6, 2026
text factualityoverall1261408.57,801N/AAug 6, 2026
text factualityexclude ties1261392.95,372N/AAug 6, 2026
text style controlindustry software and it services1261442.016,804N/AAug 6, 2026
text factualitynon english1271391.33,449N/AAug 6, 2026
textindustry entertainment and sports and media1281363.99,039N/AAug 6, 2026
text factualityhard prompts1281419.53,844N/AAug 6, 2026
textcreative writing1291363.56,690N/AAug 6, 2026
text factualityindustry software and it services1291421.01,544N/AAug 6, 2026
text style controlindustry life and physical and social science1291424.48,534N/AAug 6, 2026
textmulti turn1311396.98,951N/AAug 6, 2026
textindustry legal and government1341399.53,276N/AAug 6, 2026
textindustry writing and literature and language1371370.011,370N/AAug 6, 2026
textfrench1391381.7688N/AAug 6, 2026
textrussian1401373.33,056N/AAug 6, 2026
textspanish1431368.0984N/AAug 6, 2026
text style controlexpert1431404.72,509N/AAug 6, 2026
textlonger query1441382.89,799N/AAug 6, 2026
textoverall1451382.150,899N/AAug 6, 2026
textexclude ties1451355.036,166N/AAug 6, 2026
texthard prompts1461382.522,131N/AAug 6, 2026
textinstruction following1461366.413,272N/AAug 6, 2026
textnon english1461370.625,194N/AAug 6, 2026
text style controlchinese1461415.52,460N/AAug 6, 2026
textenglish1471390.325,653N/AAug 6, 2026
texthard prompts english1471390.011,884N/AAug 6, 2026
textindustry business and management and financial operations1491367.98,283N/AAug 6, 2026
textindustry life and physical and social science1541381.78,534N/AAug 6, 2026
textcoding1561390.39,301N/AAug 6, 2026
textexpert1571363.32,509N/AAug 6, 2026
textindustry medicine and healthcare1571379.22,789N/AAug 6, 2026
textindustry software and it services1571390.716,804N/AAug 6, 2026
text style controlmath1681373.43,221N/AAug 6, 2026
textmath1691367.63,221N/AAug 6, 2026
text style controlindustry mathematical1691371.93,051N/AAug 6, 2026
textchinese1721373.22,460N/AAug 6, 2026
textindustry mathematical1741358.03,051N/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
$2 input, $8 output per 1M
Official provider
OpenAI
Lowest third-party
N/A
Tracked offerings
1
1 rows
Columns

Show columns

OpenAIgpt-4.1global$2$81MAug 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-4.1 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-4.1Apr 14, 202528.4N/A1M32.8KNoProprietary

What is GPT-4.1?

A concise description based on the published model registry.

GPT-4.1 is OpenAI's latest and most advanced flagship model, significantly improving upon GPT-4 Turbo in performance across benchmarks, speed, and cost-effectiveness.

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-4.1 vs nearby models

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

GPT-4.1vsGemma 2 9BGPT-4.1vsLlama 3.1 8BGPT-4.1vsGPT-4GPT-4.1vsQwen3.5 4BGPT-4.1vsGPT-4oGPT-4.1vsGemini Diffusion

Models similar to GPT-4.1

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

#138+0.1
OP

GPT-4

OpenAI

28.5 LLMBoard

DetailsCompare
#141-0.5
OP

GPT-4o

OpenAI

27.9 LLMBoard

DetailsCompare
#149-5.9
OP

GPT-4.1-mini

OpenAI

22.5 LLMBoard

DetailsCompare
#109+13.1
OP

GPT-4o-mini

OpenAI

41.5 LLMBoard

DetailsCompare
#105+14.3
OP

GPT-5.4-nano

OpenAI

42.8 LLMBoard

DetailsCompare
#163-16.0
OP

GPT-3.5-Turbo

OpenAI

12.5 LLMBoard

DetailsCompare

FAQ

Common questions about GPT-4.1.

When was GPT-4.1 released?

GPT-4.1's default version was released on Apr 14, 2025.

How much does GPT-4.1 cost?

GPT-4.1's official API price is $2 per million input tokens and $8 per million output tokens via OpenAI.

Who created GPT-4.1?

GPT-4.1 is published under OpenAI in the model registry.

What is the context window for GPT-4.1?

The default version has a 1M token context window.

Is GPT-4.1 open weight?

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

How many API providers offer GPT-4.1?

1 published provider offerings are linked to the default version.

What models should I compare GPT-4.1 with?

Nearby ranked alternatives include Gemma 2 9B, Llama 3.1 8B, GPT-4.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai