NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/GPT-4.1 Mini
OpenAI logo

GPT-4.1 Mini

by OpenAI · Released Apr 2025

Multimodal1M Context
35.2
avg score
Rank #224
Compare
Better than 28% of all models
Context
1.0M tokens (~524 books)
Input $/1M
$0.40
Output $/1M
$1.60
Type
multimodal
License
Proprietary
Benchmarks
22 tested
Data as of
About

GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...

Tested on 22 benchmarks · BenchGecko score 35.2. Top scores: HELM — IFEval (90.4%), MATH level 5 (87.3%), HELM — WildBench (83.8%).

Looking for similar performance at lower cost?
Gemma 3 27B (free) scores 35.1 (100% as good) at $0.00/1M input · 100% cheaper
Capabilities
coding
27.5
#169 globally
reasoning
29.1
#121 globally
math
38.4
#159 globally
knowledge
42.2
#186 globally
general
24.3
#147 globally
language
90.4
#10 globally
Benchmark Scores
Compare All
Tested on 22 benchmarks · Ranked across 6 categories
Score Distribution (all 312 models)
0255075100
▲ You are here
codingCompare coding →
WeirdML

Unusual and adversarial machine learning challenges. Tests robustness of reasoning about edge cases in ML systems.

37.6·
Aider polyglot

Multi-language code editing from Aider. Tests editing ability across Python, JavaScript, TypeScript, Java, C++, Go, Rust, and more.

32.4·
SWE-Bench Verified (Bash Only)

SWE-bench Verified solved using only bash commands, no specialized frameworks. Tests raw terminal-based problem solving.

23.9·
reasoningCompare reasoning →
HELM — WildBench

Stanford HELM WildBench evaluation. Tests reasoning on challenging real-world tasks.

83.8·
ARC-AGI

Abstraction and Reasoning Corpus. Tests fluid intelligence through novel visual pattern recognition puzzles. Core measure of general intelligence.

3.5·
ARC-AGI-2

ARC-AGI 2, harder sequel to ARC. More complex abstract reasoning patterns that test generalization ability beyond training data.

0.1·
mathCompare math →
MATH level 5

Competition-level math from AMC, AIME, and olympiad problems. Level 5 is the hardest tier, requiring creative problem-solving.

87.3·
HELM — Omni-MATH

Stanford HELM evaluation of mathematical reasoning across diverse problem types.

49.1·
OTIS Mock AIME 2024-2025

Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.

44.7·
Quick compare:Mistral AI logovs Mistral Large 2407Google DeepMind logovs Gemma 3 27B (free)Meta logovs Llama 3.2 3B Instruct
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Model Family · OpenAI GPT-4.1
Apr 2025
37.9
$2.00/M in1.0Mctx27 benchmarks
Apr 2025
$1.00/M in(-1)1.0Mctx
Apr 2025
35.2-2.7
$0.40/M in(-0.60)1.0Mctx22 benchmarks
Apr 2025
$0.20/M in(-0.20)1.0Mctx
Apr 2025
22.4-12.8
$0.10/M in(-0.10)1.0Mctx17 benchmarks
Apr 2025
$0.05/M in(-0.05)1.0Mctx
See the full GPT-4.1 family →
Similar Models
Mistral AI logo
Mistral Large 2407
Mistral AI
35.1$2.00/1M
Google DeepMind logo
Gemma 3 27B (free)
Google DeepMind
35.1Free
Meta logo
Llama 3.2 3B Instruct
Meta
35.4$0.05/1M
Links
Info
OpenAIPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@OpenAI
BenchGecko API
gpt-4-1-mini
Specifications
  • Typemultimodal
  • Context1.0M tokens (~524 books)
  • ReleasedApr 2025
  • LicenseProprietary
  • StatusActive
  • Cost / Message~$0.002
Available On
OpenAI logoOpenAI$0.40
Categories
codingreasoningmathknowledgegenerallanguage
Learn More
context-windowtransformertokens
Share & Export
Tweet
Related Models
Mistral AI logoMistral Large 2407
35.1
Google DeepMind logoGemma 3 27B (free)
35.1
Meta logoLlama 3.2 3B Instruct
35.4
Mistral AI logoMistral Nemo
35.4
GPT-4.1 Mini is a proprietary multimodal AI model by OpenAI, released in April 2025. It has an average benchmark score of 35.2. Context window: 1M tokens.

Related Models

Mistral Large 2407 · Mistral AIGemma 3 27B (free) · Google DeepMindLlama 3.2 3B Instruct · MetaMistral Nemo · Mistral AIQwen2.5 7B Instruct · Alibaba Qwen

Benchmarks

HELM — IFEvalMATH level 5HELM — WildBenchHELM — MMLU-ProHELM — GPQA

Related Pages

OpenAI · ProviderOpenAI · EconomyAll ModelsCompare ModelsPricingDevelopers · APIContext Window · Glossary

Key facts · as of 2026-10-05

  • GPT-4.1 Mini by OpenAI. BenchGecko score 35.2, rank 224 of 312 scored models (normalized average of public benchmark scores).
  • List price $0.40 input · $1.60 output per 1M tokens (as of 2026-10-05).
  • Sold by 3 providers (as of 2026-10-05): Azure $0.40 in / $1.60 out · OpenAI $0.40 in / $1.60 out · Azure $0.44 in / $1.76 out. Every provider

How to cite · data as of 2026-10-05

GPT-4.1 Mini · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/gpt-4-1-mini

Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP