AI Progress Tracker

    GLM 5.2 · GLM 5.2

    Z.ai · 16 Jun 2026

    Ask the Advisor about this model
    76from 6
    benchmarks

    GLM 5.2 is described in reporting as an open-weights Z.ai model used to help defend Hugging Face against an AI-assisted attack. That account describes defensive use, not an established vulnerability or harmful action by GLM 5.2.

    context: 1Mtext$0.03 / $7.00 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 questions91.9%24 Jun 2026View
    SWE-bench VerifiedResolving real GitHub issues78.7%25 Jun 2026View
    OTIS Mock AIME 2024-25Competition mathematics86.4%25 Jun 2026View
    SimpleQA VerifiedShort factual questions (hallucination resistance)34.2%27 Aug 2026View
    LMArena TextHuman preference Elo from blind chat votes (not a percentage)1470 Elo22 Oct 2026View
    LMArena WebDevHuman preference Elo for building web apps (not a percentage)1604 Elo23 Oct 2026View

    Weighted mean of 4 verified benchmark results: GPQA Diamond 91.9%, SWE-bench Verified 78.7%, OTIS Mock AIME 2024-25 86.4%, SimpleQA Verified 34.2%.

    Capabilities

    • Reported use assisting Hugging Face's response to an AI-assisted attack.

    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 GLM 5.2

    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.