AI Research

    o4 Mini: gPT-5 mini succeeded o4-mini as a newer small reasoning model

    OnAirToday’s tracker verifies the model succession against OpenAI documentation

    GPT-5 mini succeeded o4-mini as a newer small reasoning model — verified by the OnAirToday AI Progress Tracker against OpenAI's published documentation.

    O

    OnAirToday

    Newsroom

    OnAirToday

    The OnAirToday AI Progress Tracker recorded a verified change to OpenAI's o4 Mini (version o4-mini): GPT-5 mini succeeded o4-mini as a newer small reasoning model.

    OpenAI o4-mini is a small reasoning model supporting text and image inputs, text output, and tool-assisted workflows, with standard API pricing of $1.10 per million input tokens and $4.40 per million output tokens. GPT-5 mini is its documented successor; this profile remains specific to o4-mini.

    What changed in this review:

    • OpenAI reports GPQA Diamond at 81.4%; this is a vendor evaluation, distinct from third-party leaderboard results.
    • Added published SWE-bench Verified and separate AIME 2024 and AIME 2025 results.
    • Flaws and limitations updated

    Teams building on o4 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/o4-mini.

    References:

    • https://platform.openai.com/docs/models/o4-mini
    • https://openai.com/index/introducing-o3-and-o4-mini/
    • https://openai.com/index/o3-o4-mini-system-card/
    • https://platform.openai.com/docs/guides/reasoning
    AI Analysis

    Generated insight by OnAirToday AI

    The documented succession signals an update to OpenAI’s lineup of small reasoning models. Tracking it helps readers distinguish the newer model from its predecessor.

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