AI Research

    GPT-5-Mini: gPQA Diamond now uses OpenAI’s published 82.3% result; the correction does not establish a model upgrade

    Tracker aligns GPQA Diamond with OpenAI’s published score

    GPQA Diamond now uses OpenAI’s published 82.3% result; the correction does not establish a model upgrade — verified by the OnAirToday AI Progress Tracker against OpenAI's published documentation.

    O

    OnAirToday

    Newsroom

    OnAirToday
    GPT-5-Mini: gPQA Diamond now uses OpenAI’s published 82.3% result; the correction does not establish a model upgrade

    The OnAirToday AI Progress Tracker recorded a verified change to OpenAI's GPT-5-Mini (version gpt-5-mini): GPQA Diamond now uses OpenAI’s published 82.3% result; the correction does not establish a model upgrade.

    GPT-5 mini is a smaller GPT-5 reasoning model supporting text and image inputs, text outputs, and tool-enabled workflows. Its documented standard API pricing is $0.25 per million input tokens and $2.00 per million output tokens, with a 400,000-token context window.

    What changed in this review:

    • SWE-bench Verified now uses OpenAI’s published 71.0% result instead of 64.7%; different evaluation configurations are not interchangeable.
    • Added OpenAI’s published AIME 2025 result of 91.1%.
    • GPT-5.1 subsequently shipped in the GPT-5 family; this profile remains specific to GPT-5 mini.
    • Flaws and limitations updated
    • Risks and threats updated

    Teams building on GPT-5-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-5-mini.

    References:

    • https://platform.openai.com/docs/models/gpt-5-mini
    • https://openai.com/index/introducing-gpt-5-for-developers/
    • https://platform.openai.com/docs/models/gpt-4o-mini
    • https://openai.com/index/gpt-5-1/
    AI Analysis

    Generated insight by OnAirToday AI

    Accurate benchmark records help readers compare model results against published documentation. A corrected score should not be mistaken for evidence that the model itself changed.

    Powered by AI • Not a substitute for human analysisMore Insights →

    Key takeaways

    Generated insight by OnAirToday AI

    • GPT-5-Mini: gPQA Diamond now uses OpenAI’s published 82.3% result; the correction does not establish a model upgrade
    • GPQA Diamond now uses OpenAI’s published 82.3% result; the correction does not establish a model upgrade — verified by the OnAirToday AI Progress Tracker against OpenAI's published documentation.
    • Tracker aligns GPQA Diamond with OpenAI’s published score

    Why it matters: GPT-5-Mini: gPQA Diamond now uses OpenAI’s published 82.3% result; the correction does not establish a model upgrade

    Read the full story at OnAirToday →
    Share
    Filed under:AI Research

    Comments

    Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.

    0/1000