Comprehensive side-by-side LLM comparison
GPT-4.1 leads with 50.7% higher average benchmark score. GPT-4.1 offers 1.1M more tokens in context window than GPT-3.5 Turbo. GPT-3.5 Turbo is $8.00 cheaper per million tokens. GPT-4.1 supports multimodal inputs. Overall, GPT-4.1 is the stronger choice for coding tasks.
OpenAI
GPT-3.5 Turbo was developed as an optimized version of GPT-3.5, designed to provide a balance of capability and efficiency for conversational and completion tasks. Built to serve as a cost-effective option for applications requiring reliable language understanding and generation, it became widely adopted for chatbots, content generation, and general-purpose AI assistance.
OpenAI
GPT-4.1 represents an iterative improvement in the GPT-4 series, developed to refine the foundational capabilities established by GPT-4. Built to incorporate learnings and optimizations from the deployment of previous versions, it continues the evolution of OpenAI's flagship model line with enhanced reliability and performance.
2 years newer

GPT-3.5 Turbo
OpenAI
2023-03-21

GPT-4.1
OpenAI
2025-04-14
Cost per million tokens (USD)

GPT-3.5 Turbo

GPT-4.1
Context window and performance specifications
Average performance across 4 common benchmarks

GPT-3.5 Turbo

GPT-4.1
GPT-3.5 Turbo
2021-09-30
GPT-4.1
2024-06-01
Available providers and their performance metrics

GPT-3.5 Turbo
Azure
OpenAI


GPT-3.5 Turbo

GPT-4.1

GPT-3.5 Turbo

GPT-4.1
GPT-4.1
OpenAI