GPT-4.1 Mini: openAI’s published launch evaluation reports GPQA Diamond at 65.0%, rather than 65.8%
A tracker’s check of OpenAI documentation finds a different GPQA Diamond figure
OpenAI’s published launch evaluation reports GPQA Diamond at 65.0%, rather than 65.8% — 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-4.1 Mini (version gpt-4.1-mini-2025-04-14): OpenAI’s published launch evaluation reports GPQA Diamond at 65.0%, rather than 65.8%.
GPT-4.1 mini is OpenAI’s compact GPT-4.1 model for instruction following, coding, text generation and image understanding. Its documented API specification provides a roughly one-million-token context window, with standard text pricing of $0.40 per million input tokens and $1.60 per million output tokens.
What changed in this review:
- Added OpenAI’s published MMMU result of 72.7%.
- Flaws and limitations updated
- Risks and threats updated
Teams building on GPT-4.1 Mini 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-mini.
References:
- https://platform.openai.com/docs/models/gpt-4.1-mini
- https://openai.com/index/gpt-4-1/
Generated insight by OnAirToday AI
Benchmark scores shape how researchers compare AI models, so even a small difference can affect interpretation. Checking published documentation helps clarify which figure was reported.
Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.