DeepYard
G

GPT-4.1

10

GPT-4.1 is a flagship large language model optimized for advanced instruction fo...

commercialpaid

About

GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and ente

Details

Modalityimage, file, text
Context Window1.0M tokens
Release DateApr 14, 2025
API AvailableYes
Hostingapi
Output Speed220 tokens/sec
Time to First Token350ms
Quality Index80/100
Coding Index73/100
Reasoning Index78/100

Benchmarks

Chatbot Arena ELO
1410/1500
MMLU-Pro
82.4/100
SWE-bench Verified
54.6/100
MATH-500
84.2/100
GPQA Diamond
66.3/100
HumanEval
92.1/100

Tags

multimodallong-contextapichatfrontier