Home/Models/GPT-4.1 Nano
OpenAI logo

GPT-4.1 Nano

by OpenAI · Released Apr 2025

Multimodal1M Context
25.8
avg score
Rank #192
Compare
Better than 18% of all models
Context
1.0M tokens (~524 books)
Input $/1M
$0.10
Output $/1M
$0.40
Type
multimodal
License
Proprietary
Benchmarks
14 tested
Data updated today
About

For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...

Tested on 14 benchmarks with 35.2% average. Top scores: HELM — IFEval (84.3%), HELM — WildBench (81.1%), MATH level 5 (70.0%).

Looking for similar performance at lower cost?
Gemma 3 27B scores 25.1 (97% as good) at $0.08/1M input · 20% cheaper
Capabilities
coding
13.9
#134 globally
reasoning
27.1
#91 globally
math
34.1
#122 globally
knowledge
40.7
#149 globally
language
84.3
#34 globally
Benchmark Scores
Compare All
Tested on 14 benchmarks · Ranked across 5 categories
Score Distribution (all 233 models)
0255075100
▲ You are here
WeirdML

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

19.0
Aider polyglot

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

8.9
HELM — WildBench

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

81.1
ARC-AGI-2

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

0.1
ARC-AGI

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

0.1
MATH level 5

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

70.0
HELM — Omni-MATH

Stanford HELM evaluation of mathematical reasoning across diverse problem types.

36.7
OTIS Mock AIME 2024-2025

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

28.8
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Documentation
Community
BenchGecko API
gpt-4-1-nano
Specifications
  • Typemultimodal
  • Context1.0M tokens (~524 books)
  • ReleasedApr 2025
  • LicenseProprietary
  • StatusActive
  • Cost / Message~$0.001
Available On
OpenAI logoOpenAI$0.10
Share & Export
Tweet
GPT-4.1 Nano is a proprietary multimodal AI model by OpenAI, released in April 2025. It has an average benchmark score of 25.8. Context window: 1M tokens.