GPT-4.1 Nano: gPQA Diamond now reports OpenAI’s published launch result of 50.3%, replacing 48.9%

The OnAirToday AI Progress Tracker recorded a verified change to OpenAI's GPT-4.1 Nano (version gpt-4.1-nano-2025-04-14): GPQA Diamond now reports OpenAI’s published launch result of 50.3%, replacing 48.9%.

GPT-4.1 nano is a low-cost OpenAI API model designed for fast tasks such as classification and autocompletion, with a context window exceeding one million tokens. It supports text and image inputs, text outputs and tool calling, but its published benchmark performance makes it a weaker choice for demanding reasoning and code-editing tasks.

What changed in this review:

• Aider Polyglot now reports OpenAI’s published launch result of 9.8%, replacing 8.9%.
• Unconfirmed OTIS Mock AIME, FrontierMath, SimpleQA Verified and MATH Level 5 scores are no longer reported.

Teams building on GPT-4.1 Nano should confirm limits, pricing and benchmark coverage against the vendor's own documentation before relying on these figures.

The full profile — capabilities, benchmark citations, known flaws and risk guidance — is on the tracker at /ai-models/gpt-4-1-nano.

References:

• https://platform.openai.com/docs/models/gpt-4.1-nano
• https://openai.com/index/gpt-4-1/
• https://platform.openai.com/docs/guides/function-calling