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

OpenAI model product

GPT-4.1-mini

GPT-4.1 mini provides a balance between intelligence, speed, and cost. It's a significant leap in small model performance, even beating GPT-4o in many benchmarks while reducing latency and cost.

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

Compare
LLMBoard score22.5GPT-4.1 mini
Coverage80%13 benchmark families
Context window1MTokens
Official input price$0.40OpenAI 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 mini
Released
Apr 14, 2025
Knowledge cutoff
May 31, 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 mini category scores

Benchmark results

Published benchmark records for the scored version GPT-4.1 mini.

28 rows
Columns

Show columns

OpenAI-MRCR: 2 needle 1M0.34525.0%CAug 7, 2026
ComplexFuncBench0.55733.3%CAug 7, 2026
Internal API instruction following (hard)0.55733.3%CAug 7, 2026
OpenAI-MRCR: 2 needle 128k0.55950.0%CAug 7, 2026
CharXiv-D0.961666.7%CAug 7, 2026
Aider-Polyglot Edit0.381022.2%CAug 7, 2026
Graphwalks parents <128k0.681858.8%CAug 7, 2026
COLLIE0.591011.1%CAug 7, 2026
MathVista0.793979.0%CAug 7, 2026
Graphwalks BFS <128k0.6132242.9%CAug 7, 2026
Graphwalks parents >128k0.1161811.8%CAug 7, 2026
Multi-IF0.7172015.8%CAug 7, 2026
Aider-Polyglot0.3192214.3%CAug 7, 2026
TAU-bench Airline0.4202313.6%CAug 7, 2026
Graphwalks BFS >128k0.121224.8%CAug 7, 2026
TAU-bench Retail0.6222512.5%CAug 7, 2026
MMLU0.92310077.8%CAug 7, 2026
Multi-Challenge0.4262910.7%CAug 7, 2026
MMMU0.7276358.1%CAug 7, 2026
HMMT 20250.331336.3%CAug 7, 2026
CharXiv-R0.6374721.7%CAug 7, 2026
MMMLU0.8404918.8%CAug 7, 2026
IFEval0.8416537.5%CAug 7, 2026
AIME 20240.5475311.5%CAug 7, 2026
Humanity's Last Exam0.092920.0%CAug 7, 2026
SWE-Bench Verified0.21011042.9%CAug 7, 2026
AIME 20250.41091144.4%CAug 7, 2026
GPQA0.715023335.8%CAug 7, 2026

Arena results

Preference and agent-evaluation signals from published Arena datasets.

80 rows
Columns

Show columns

vision style controlcaptioning161195.2397N/AAug 6, 2026
vision style controlcreative writing221187.31,276N/AJan 9, 2026
visioncaptioning241176.3397N/AAug 6, 2026
vision style controlentity recognition251198.3360N/AAug 6, 2026
visioncreative writing291164.91,276N/AJan 9, 2026
visionentity recognition371188.2360N/AAug 6, 2026
vision style controlcreative writing vision521217.61,172N/AAug 6, 2026
vision style controlhumor531196.51,426N/AAug 6, 2026
vision style controlchinese621226.41,139N/AAug 6, 2026
visionhumor631181.31,426N/AAug 6, 2026
visioncreative writing vision671194.01,172N/AAug 6, 2026
visionchinese681189.41,139N/AAug 6, 2026
vision style controlenglish681208.619,809N/AAug 6, 2026
vision style controloverall691202.640,833N/AAug 6, 2026
visionhomework701215.31,333N/AAug 6, 2026
vision style controlhomework711222.21,333N/AAug 6, 2026
vision style controlocr741206.510,604N/AAug 6, 2026
vision style controldiagram761208.72,400N/AAug 6, 2026
visionocr781188.110,604N/AAug 6, 2026
visiondiagram801182.12,400N/AAug 6, 2026
visionenglish821191.219,809N/AAug 6, 2026
visionoverall831182.540,833N/AAug 6, 2026
text style controlgerman1181391.21,017N/AAug 6, 2026
text style controlkorean1201347.2781N/AAug 6, 2026
text style controljapanese1271324.1909N/AAug 6, 2026
text style controlpolish1281382.12,616N/AAug 6, 2026
text style controlfrench1351405.0529N/AAug 6, 2026
textjapanese1441285.9909N/AAug 6, 2026
text style controlindustry legal and government1491398.12,477N/AAug 6, 2026
text style controlmulti turn1501392.27,183N/AAug 6, 2026
text style controlcoding1511433.66,911N/AAug 6, 2026
textgerman1521348.21,017N/AAug 6, 2026
textkorean1541297.5781N/AAug 6, 2026
text style controlcreative writing1541349.65,141N/AAug 6, 2026
text style controllonger query1551389.87,036N/AAug 6, 2026
text style controlenglish1561397.919,750N/AAug 6, 2026
textpolish1571328.82,616N/AAug 6, 2026
text style controlhard prompts1581402.516,228N/AAug 6, 2026
text style controlindustry business and management and financial operations1581379.56,057N/AAug 6, 2026
text style controlindustry entertainment and sports and media1581348.76,779N/AAug 6, 2026
text style controlindustry software and it services1581419.012,729N/AAug 6, 2026
text style controlinstruction following1581372.710,058N/AAug 6, 2026
text style controlexclude ties1591359.227,891N/AAug 6, 2026
text style controlhard prompts english1591413.08,737N/AAug 6, 2026
text style controlindustry writing and literature and language1591360.68,678N/AAug 6, 2026
textfrench1601355.0529N/AAug 6, 2026
text style controloverall1601383.039,277N/AAug 6, 2026
text style controlindustry medicine and healthcare1611397.72,322N/AAug 6, 2026
text style controlnon english1631360.019,521N/AAug 6, 2026
text style controlspanish1641357.2721N/AAug 6, 2026
text style controlrussian1661361.22,627N/AAug 6, 2026
text style controlexpert1681382.42,001N/AAug 6, 2026
text style controlindustry life and physical and social science1711384.56,528N/AAug 6, 2026
textmulti turn1721352.87,183N/AAug 6, 2026
textexpert1751337.02,001N/AAug 6, 2026
textinstruction following1761332.310,058N/AAug 6, 2026
textlonger query1761344.07,036N/AAug 6, 2026
textcoding1771367.66,911N/AAug 6, 2026
text style controlchinese1771383.62,047N/AAug 6, 2026
text style controlindustry mathematical1781364.12,478N/AAug 6, 2026
textspanish1801308.1721N/AAug 6, 2026
texthard prompts1841349.016,228N/AAug 6, 2026
textindustry legal and government1841344.82,477N/AAug 6, 2026
text style controlmath1841353.82,689N/AAug 6, 2026
textoverall1851340.839,277N/AAug 6, 2026
texthard prompts english1851361.68,737N/AAug 6, 2026
textindustry writing and literature and language1851319.08,678N/AAug 6, 2026
textexclude ties1861296.927,891N/AAug 6, 2026
textindustry mathematical1861346.32,478N/AAug 6, 2026
textindustry software and it services1881361.012,729N/AAug 6, 2026
textrussian1881317.42,627N/AAug 6, 2026
textindustry entertainment and sports and media1891301.16,779N/AAug 6, 2026
textmath1891343.12,689N/AAug 6, 2026
textnon english1891317.019,521N/AAug 6, 2026
textenglish1901356.619,750N/AAug 6, 2026
textindustry business and management and financial operations1901321.46,057N/AAug 6, 2026
textcreative writing1921300.75,141N/AAug 6, 2026
textchinese1951329.12,047N/AAug 6, 2026
textindustry medicine and healthcare1981326.12,322N/AAug 6, 2026
textindustry life and physical and social science2031328.06,528N/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
$0.40 input, $1.6 output per 1M
Official provider
OpenAI
Lowest third-party
From $0.40 input, $1.6 output per 1M via Helicone
Tracked offerings
2
2 rows
Columns

Show columns

Heliconegpt-4.1-mini-2025-04-14global$0.40$1.61MAug 7, 2026
OpenAIgpt-4.1-miniglobal$0.40$1.61MAug 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-mini 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-4.1 miniApr 14, 202522.5N/A1M32.8KNoProprietary

What is GPT-4.1-mini?

A concise description based on the published model registry.

GPT-4.1 mini provides a balance between intelligence, speed, and cost. It's a significant leap in small model performance, even beating GPT-4o in many benchmarks while reducing latency and cost.

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-mini vs nearby models

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

GPT-4.1-minivsQwen2.5 Coder 7BGPT-4.1-minivsQwen3 VL 4B ThinkingGPT-4.1-minivsMinistral 8BGPT-4.1-minivsGemma 3n E4B LiteRTGPT-4.1-minivsGemma 3 4BGPT-4.1-minivsJamba 1.5 Mini

Models similar to GPT-4.1-mini

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

#141+5.3
OP

GPT-4o

OpenAI

27.9 LLMBoard

DetailsCompare
#139+5.9
OP

GPT-4.1

OpenAI

28.4 LLMBoard

DetailsCompare
#138+6.0
OP

GPT-4

OpenAI

28.5 LLMBoard

DetailsCompare
#163-10.1
OP

GPT-3.5-Turbo

OpenAI

12.5 LLMBoard

DetailsCompare
#164-11.1
OP

GPT-4.1-nano

OpenAI

11.4 LLMBoard

DetailsCompare
#109+19.0
OP

GPT-4o-mini

OpenAI

41.5 LLMBoard

DetailsCompare

FAQ

Common questions about GPT-4.1-mini.

When was GPT-4.1-mini released?

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

How much does GPT-4.1-mini cost?

GPT-4.1-mini's official API price is $0.40 per million input tokens and $1.6 per million output tokens via OpenAI. The lowest tracked third-party offer starts at $0.40 input and $1.6 output via Helicone.

Who created GPT-4.1-mini?

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

What is the context window for GPT-4.1-mini?

The default version has a 1M token context window.

Is GPT-4.1-mini open weight?

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

How many API providers offer GPT-4.1-mini?

2 published provider offerings are linked to the default version.

What models should I compare GPT-4.1-mini with?

Nearby ranked alternatives include Qwen2.5 Coder 7B, Qwen3 VL 4B Thinking, Ministral 8B.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai