AI Progress Tracker

    Claude Opus 4.8 · claude-opus-4-8

    Anthropic · 28 May 2026

    Ask the Advisor about this model
    74from 6
    benchmarks

    Not yet confirmed by public reporting. Documentation and incident reports concerning other Claude Opus versions do not establish Claude Opus 4.8’s specifications, performance, or safety record.

    context: 1Mtextimagefile

    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%7 Jun 2026View
    OTIS Mock AIME 2024-25Competition mathematics98.3%7 Jun 2026View
    FrontierMath47.2%8 Jun 2026View
    SimpleQA VerifiedShort factual questions (hallucination resistance)53%27 Aug 2026View
    LMArena TextHuman preference Elo from blind chat votes (not a percentage)1461 Elo22 Oct 2026View
    LMArena WebDevHuman preference Elo for building web apps (not a percentage)1556 Elo23 Oct 2026View

    Weighted mean of 4 verified benchmark results: GPQA Diamond 91%, OTIS Mock AIME 2024-25 98.3%, FrontierMath 47.2%, SimpleQA Verified 53%.

    Security & risk dashboardLatest vulnerabilities, advisories and real-world incidents for Claude Opus 4.8

    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.