AI Progress Tracker

    Claude Opus 5.5 · claude-opus-5-5

    Anthropic · 22 Sep 2026

    Ask the Advisor about this model
    88from 5
    benchmarks

    Claude Opus 5.5 release status: Not yet confirmed by public reporting. Model-specific specifications, performance, and safety findings: Not yet confirmed by public reporting.

    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 questions90.6%22 Sep 2026View
    OTIS Mock AIME 2024-25Competition mathematics100%22 Sep 2026View
    SimpleQA VerifiedShort factual questions (hallucination resistance)72.2%22 Sep 2026View
    LMArena TextHuman preference Elo from blind chat votes (not a percentage)1516 Elo22 Oct 2026View
    LMArena WebDevHuman preference Elo for building web apps (not a percentage)1807 Elo23 Oct 2026View

    Weighted mean of 3 verified benchmark results: GPQA Diamond 90.6%, OTIS Mock AIME 2024-25 100%, SimpleQA Verified 72.2%.

    Security & risk dashboardLatest vulnerabilities, advisories and real-world incidents for Claude Opus 5.5

    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.