AI Progress Tracker

    GPT-5.4 Mini · gpt-5.4-mini

    OpenAI · 17 Mar 2026

    Ask the Advisor about this model
    62from 6
    benchmarks

    GPT-5.4 Mini is identified as an OpenAI model with the identifier gpt-5.4-mini. Current documented state: Not yet confirmed by public reporting.

    context: 400Kfileimagetext$0.75 / $4.50 per 1M tokens (in / out)

    Benchmark results

    Every figure links to where it was published. Compare like with like — harnesses and prompt setups differ between vendors.

    BenchmarkScoreSource
    GPQA DiamondPhD-level science questions86.9%7 Aug 2026View
    OTIS Mock AIME 2024-25Competition mathematics88.9%7 Aug 2026View
    FrontierMath28.3%15 Apr 2026View
    SimpleQA VerifiedShort factual questions (hallucination resistance)29.4%27 Aug 2026View
    LMArena TextHuman preference Elo from blind chat votes (not a percentage)1412 Elo22 Oct 2026View
    LMArena WebDevHuman preference Elo for building web apps (not a percentage)1397 Elo23 Oct 2026View

    Weighted mean of 4 verified benchmark results: GPQA Diamond 86.9%, OTIS Mock AIME 2024-25 88.9%, FrontierMath 28.3%, SimpleQA Verified 29.4%.

    Capabilities

    • Not yet confirmed by public reporting.

    What improved

    • Not yet confirmed by public reporting.

    Known flaws & limitations

    • Not yet confirmed by public reporting.

    Risks, safety & security issues

    • Not yet confirmed by public reporting.

    Good fit for

    • Not yet confirmed by public reporting.

    Poor fit for

    • Not yet confirmed by public reporting.
    Security & risk dashboardLatest vulnerabilities, advisories and real-world incidents for GPT-5.4 Mini

    References

    Profile last reviewed 10/27/2026 and re-checked automatically every few hours against the vendor's published documentation, papers and public leaderboards. Scores come from the cited benchmark results above — confirm limits and pricing against the provider's own documentation before building on them.