GPT-5-Nano: benchmark coverage now includes OpenAI's published launch results: GPQA Diamond 71.2% and AIME 2025 85.2%
Tracker adds GPT-5-Nano’s published scores on two benchmarks
Benchmark coverage now includes OpenAI's published launch results: GPQA Diamond 71.2% and AIME 2025 85.2% — verified by the OnAirToday AI Progress Tracker against OpenAI's published documentation.
OnAirToday
Newsroom
The OnAirToday AI Progress Tracker recorded a verified change to OpenAI's GPT-5-Nano (version gpt-5-nano): Benchmark coverage now includes OpenAI's published launch results: GPQA Diamond 71.2% and AIME 2025 85.2%.
GPT-5 nano is a low-cost reasoning model designed for tasks such as summarization and classification, with text and image inputs and text-only output. Its documented specifications include a 400,000-token context window, up to 128,000 output tokens, and standard API pricing of $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://platform.openai.com/docs/models/gpt-4.1-nano
- https://openai.com/index/gpt-5-system-card/
Generated insight by OnAirToday AI
Adding the published scores makes GPT-5-Nano’s benchmark record easier to compare across evaluation sets. Verification against OpenAI documentation also clarifies the source of the results.
Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.