GPT-5-Nano: benchmark coverage now uses OpenAI's published launch results: GPQA Diamond 71.2% and AIME 2025 85.2%

The OnAirToday AI Progress Tracker recorded a verified change to OpenAI's GPT-5-Nano (version gpt-5-nano): Benchmark coverage now uses OpenAI's published launch results: GPQA Diamond 71.2% and AIME 2025 85.2%.

GPT-5 nano is a compact GPT-5 reasoning model designed for fast, economical tasks such as summarization and classification, with text and image inputs and text output. Standard API pricing is $0.05 per million input tokens and $0.40 per million output tokens.

Teams building on GPT-5-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-5-nano.

References:

• https://platform.openai.com/docs/models/gpt-5-nano
• https://openai.com/index/introducing-gpt-5-for-developers/
• https://openai.com/index/gpt-5-system-card/
• https://platform.openai.com/docs/models/gpt-4.1-nano