Claude Opus 5.5 · 官方评测披露
Claude Opus 5.5 当前收录 41 项测试的官方记录。已完成列明材料的核查。
模型发布 · Claude Opus
官方材料与核查范围
Current Opus 5.5 System Card pp.1-230 and the official release table are complete; the Haiku 5.5 comparison card pp.1-144 is complete from the combined Singer/Boyle review; the later Fable 5.2 article and all nine charts were fully reviewed by the parent. The Fable comparison is later evidence and does not change launch availability. 核对时间 。
当前资料不足以还原首发。 没有发布当日历史快照。
- Introducing Claude Opus 5.5 · 主文 · 官方发布页;本地保存 HTML/TXT:本地留存副本、本地留存副本;主表为 HTML;原文发布日期 2026-09-22,当前修订时间未知公布 未确认 · 采集 · 已核查 已补完当前发布主文全文、全部引言与脚注,实际查看全部13个figure及正文/品牌图像。核读与图片清单见本地留存副本。未估读无数值曲线,客户私有评测或缺方法的引述不自动作为普通能力成绩。
- Claude Opus 5.5 System Card · 附件 · 官方当前 System Card;封面日期 2026-09-22;本地 PDF/TXT:本地留存副本、current-opus-5-5-system-card.txt;230 页全文核读;当前修订时间未知公布 未确认 · 采集 · 已核查 当前保存版 230 页全文核读;230 个 TXT 页段连续且无替换字符;63 张双页接触表覆盖 126 个含图页,全部逐张实际查看,并放大查看原 PDF pp.187-188。
- Claude Haiku 5.5 System Card (Opus 5.5 OSWorld offline comparison) · 附件 · Official current System Card, cover dated 2026-10-07; current PDF/TXT saved at 本地留存副本 and .txt; full pp.1-144 read across Singer/Boyle reviews, with 63 safety figure pages visually checked; current revision date unknown.公布 未确认 · 采集 · 已核查 Singer/Boyle combined current-card review covers all pp.1-144; 144 continuous TXT page segments; 63 safety figure pages visually checked; pp.111-139 capability section was previously read by Boyle. This completes the auxiliary source review; it does not establish launch-day bytes.
- Introducing Claude Fable 5.2 and Claude Mythos 5.2 · 主文 · Official article published 2026-11-09 and edited 2026-11-11; current HTML/TXT saved at 本地留存副本 and .txt; later Opus 5.5 comparison, not launch-day evidence.公布 · 采集 · 已核查 Parent completed the full official Fable 5.2 article and viewed all nine charts; RoboDojo chart 8 was visually verified for the Opus 5.5 39.4% Max-effort bar and internal-run/highest-effort footnote. This is later-comparison evidence only.
配置
- Adaptive Max · 官方主表标准配置为 adaptive thinking/max effort、默认 temperature/top_p;具体工具、safeguards、fallback 与运行数按各评测章节记录,不将其一概视为生产 safeguards enabled。 max未知项 表格没有为每个 benchmark 单独列出采样设置和运行数;章节明确列出的差异优先。
- Terminal-Bench xhigh · Terminal-Bench 4.0 使用 xhigh effort;官方说明这是 Opus 5.5 的最高分设置。 xhigh未知项 每题运行数未在该主表脚注具体给出。
- HLE 有工具 · Humanity's Last Exam; with tools; adaptive thinking/max effort per table note。 max未知项 具体题集和 trial count 未列。
- System Card OSWorld 2.0 更新协议 · 108 个 long-horizon desktop tasks;五次独立运行;1080p、最多 500 steps、max effort;更新 task/assets 与 harness。 max未知项 Card 当前修订日期未公布;与主文 OSWorld 2.1 标签对应关系不明确。
- OSWorld 2.1 offline subset · Haiku 5.5 System Card 报告 82/108 offline tasks、no internet、五次尝试;max effort。 max未知项 该卡当前修订日期未公布。
- System Card max effort (per-result benchmark harnesses) · System Card §8.1 default: adaptive thinking/max effort and default sampling settings unless a section says otherwise. Benchmark tools, evaluator, safeguards, fallback, and repetitions remain per-result conditions; this config represents the stated model effort, not harness equivalence. max未知项 Exact run time is not disclosed.、Per-benchmark tools, safeguards, and repetition counts are specified only where the source states them.
- FrontierCode v1.1 Main medium effort · Explicit medium effort; Cognition evaluation in Claude Code. Mean@5. medium未知项 No API-equivalent harness or run date is stated.
- FrontierCode v1.1 Extended medium effort · Explicit medium effort; Cognition evaluation in Claude Code. Mean@5. medium未知项 No API-equivalent harness or run date is stated.
- FrontierCode v1.1 Extended max effort · Explicit max effort; Cognition evaluation in Claude Code. Mean@5. max未知项 No API-equivalent harness or run date is stated.
- CursorBench 4.0 medium effort · Explicit medium effort in Cursor's production agent harness; Cursor measured the score. medium未知项 No API-equivalent harness or run date is stated.
- CursorBench 4.0 high effort · Explicit high effort in Cursor's production agent harness; Cursor measured the score. high未知项 No API-equivalent harness or run date is stated.
- CursorBench 4.0 xhigh effort · Explicit xhigh effort in Cursor's production agent harness; Cursor measured the score. xhigh未知项 No API-equivalent harness or run date is stated.
- HLE no tools, low effort · Reasoning-only; explicit low effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader. low未知项 The figure does not state the number of model trials.
- HLE no tools, medium effort · Reasoning-only; explicit medium effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader. medium未知项 The figure does not state the number of model trials.
- HLE no tools, high effort · Reasoning-only; explicit high effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader. high未知项 The figure does not state the number of model trials.
- HLE no tools, xhigh effort · Reasoning-only; explicit xhigh effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader. xhigh未知项 The figure does not state the number of model trials.
- HLE no tools, max effort · Reasoning-only; explicit max effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader. max未知项 The figure does not state the number of model trials.
- HLE with tools, low effort · Web search, web fetch, programmatic tool calling, and code execution; explicit low effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader. low未知项 The figure does not state the number of model trials.
- HLE with tools, medium effort · Web search, web fetch, programmatic tool calling, and code execution; explicit medium effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader. medium未知项 The figure does not state the number of model trials.
- HLE with tools, high effort · Web search, web fetch, programmatic tool calling, and code execution; explicit high effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader. high未知项 The figure does not state the number of model trials.
- HLE with tools, xhigh effort · Web search, web fetch, programmatic tool calling, and code execution; explicit xhigh effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader. xhigh未知项 The figure does not state the number of model trials.
- DRACO low effort, in-house agent harness · Explicit low effort; web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget. low未知项 Model run date and direct API reproduction are not stated.
- DRACO medium effort, in-house agent harness · Explicit medium effort; web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget. medium未知项 Model run date and direct API reproduction are not stated.
- DRACO high effort, in-house agent harness · Explicit high effort; web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget. high未知项 Model run date and direct API reproduction are not stated.
- DRACO xhigh effort, in-house agent harness · Explicit xhigh effort; web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget. xhigh未知项 Model run date and direct API reproduction are not stated.
- DRACO max effort, in-house agent harness · Explicit max effort; web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget. max未知项 Model run date and direct API reproduction are not stated.
- WANDR low effort, frozen-index harness · Explicit low effort; web search and web fetch limited to a frozen index; programmatic tool calling and code execution; 980k-token task budget. low未知项 Model run date and direct API reproduction are not stated.
- WANDR medium effort, frozen-index harness · Explicit medium effort; web search and web fetch limited to a frozen index; programmatic tool calling and code execution; 980k-token task budget. medium未知项 Model run date and direct API reproduction are not stated.
- WANDR high effort, frozen-index harness · Explicit high effort; web search and web fetch limited to a frozen index; programmatic tool calling and code execution; 980k-token task budget. high未知项 Model run date and direct API reproduction are not stated.
- WANDR xhigh effort, frozen-index harness · Explicit xhigh effort; web search and web fetch limited to a frozen index; programmatic tool calling and code execution; 980k-token task budget. xhigh未知项 Model run date and direct API reproduction are not stated.
- WANDR max effort, frozen-index harness · Explicit max effort; web search and web fetch limited to a frozen index; programmatic tool calling and code execution; 980k-token task budget. max未知项 Model run date and direct API reproduction are not stated.
- Chartography max effort, no tools · Adaptive thinking/max effort; no tools; five runs; Gemini 3.5 Flash grader. max
- Chartography max effort, with tools · Adaptive thinking/max effort; container, standard libraries, and image-cropping tool; five runs; Gemini 3.5 Flash grader. max
- BenchCAD Vision2Code max effort, no tools · Adaptive thinking/max effort; corrected 256 x 256 px per view implementation; random 1,000-file subset; five runs. max未知项 Task-level variance is not separately reported in the card text.
- BenchCAD Vision2Code max effort, with tools · Adaptive thinking/max effort; container, standard libraries, and image-cropping tool; corrected 256 x 256 px per view implementation; random 1,000-file subset; five runs. max未知项 Task-level variance is not separately reported in the card text.
- GDPval-AA v2.1 xhigh effort · Explicit xhigh effort; Artificial Analysis independent harness; 220 tasks across 44 occupations. xhigh未知项 Run date is not stated.
- AA-Briefcase v1.1 high effort · Explicit high effort; Artificial Analysis independent harness. high未知项 Run date is not stated.
- AA-Briefcase v1.1 xhigh effort · Explicit xhigh effort; Artificial Analysis independent harness. xhigh未知项 Run date is not stated.
- AA-Briefcase v1.1 max effort · Explicit max effort; Artificial Analysis independent harness. max未知项 Run date is not stated.
- Toolathlon-Verified max effort with safeguards · Adaptive thinking/max effort; production safety classifiers and sandbox-escape monitor enabled; three trials per task; all stopped trials counted as failures. max
- HealthBench max effort with safeguards · Adaptive thinking/max effort; safety classifiers enabled and refusal fallback to Opus 5; no tools or customized system prompts; five trials. max
- HealthBench Professional max effort with safeguards · Adaptive thinking/max effort; safety classifiers enabled and refusal fallback to Opus 5; no tools or customized system prompts; five trials. max
- RoboDojo Sim internal run, max effort · Official Fable 5.2 article chart labels Opus 5.5 Max effort; footnote says RoboDojo Sim used internally run models at their highest-available effort. max未知项 RoboDojo version, task count, prompt/harness, trial count, and run date are not stated.
直接前代与后续发布
直接前代 Claude Opus 5。 官方关系依据
Opus 5.5 is a major step up from Opus 5.
25 项披露延续 · 16 项新增 · 21 项本次未见 · 0 项待核查
测试记录 · 41
- Terminal-Bench · 4.0本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- FrontierCode · v1.1 Main set本次发布有 2 条成绩记录,含 2 条精确值(可含历史记录)
- CursorBench · 4.0本次发布有 4 条成绩记录,含 4 条精确值(可含历史记录)
- GDPval-AA · v2.1本次发布有 2 条成绩记录,含 2 条精确值(可含历史记录)
- AutomationBench · Zapier 私有 early-access set;版本未注明本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- Humanity's Last Exam · 2,500-question benchmark本次发布有 10 条成绩记录,含 10 条精确值(可含历史记录)
- Terminal-Bench-Science · 0.1本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- OSWorld · 2.1 (September 10, 2026 task/assets release)本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- Chartography · 100 tasks本次发布有 2 条成绩记录,含 2 条精确值(可含历史记录)
- OSWorld · System Card 所称 2.0;2026-09-10 任务与资源版本、108 题、更新 harness本次发布有 2 条成绩记录,含 2 条精确值(可含历史记录)
- OSWorld · 2.1, 82-task offline no-internet subset, partial score本次发布有 2 条成绩记录,含 2 条精确值(可含历史记录)
- SWE-bench Pro · Pro本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- DeepSWE · v1.1本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- FrontierSWE · v2本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- DRACO · 100-task Perplexity deep-research benchmark本次发布有 5 条成绩记录,含 5 条精确值(可含历史记录)
- WANDR · 500-task wide research benchmark本次发布有 5 条成绩记录,含 5 条精确值(可含历史记录)
- ProgramBench · 166 个保留的 golden tasks;架构与时限按协议区分本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- BenchCAD Vision2Code · 1,000-file random subset of 17,900 files本次发布有 2 条成绩记录,含 2 条精确值(可含历史记录)
- OfficeQA · Full set本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- Legal Agent Benchmark · Opus 5 官方发布表所列 held-out set本次发布有 2 条成绩记录,含 2 条精确值(可含历史记录)
- AA-Briefcase · v1.1本次发布有 3 条成绩记录,含 3 条精确值(可含历史记录)
- Toolathlon-Verified · June 2026 finalized release本次发布有 4 条成绩记录,含 4 条精确值(可含历史记录)
- HealthBench · 48,000+ rubric items across 5,000 multi-turn conversations本次发布有 2 条成绩记录,含 2 条精确值(可含历史记录)
- HealthBench Professional · 525 physician-authored conversations本次发布有 2 条成绩记录,含 2 条精确值(可含历史记录)
- Global MMLU · 42 languages including English · overall average本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- Multi-task Indic Language Understanding Benchmark · 10 Indic languages plus English · overall average本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- SpatialBench Verified · Verified本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- Morphology-to-molecule matching · Four multi-channel human-liver in-vitro cell imaging sets matched to shuffled molecule-dose perturbations本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- Medicinal Chemistry ADME · 504 drug-discovery questions about measured ADME properties本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- Protein Design Sequence Generation · Protein sequence generation conditioned on design constraints本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- De novo protein binder design · System Card evaluation; 15 targets; 30 miniprotein binders per target; Cas9 excluded本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- Biomedical Image Analysis · System-card evaluation across public biomedical-image competition tasks; included competition set unspecified本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- Protocol Troubleshooting · System-card protocol troubleshooting variant; task count unspecified本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- RoboDojo Sim · 版本/任务配置未注明本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- SWE-bench Multilingual · 300 problems, 9 programming languages本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- SWE-bench Multimodal · Multimodal本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- FrontierCode · v1.1 Extended set本次发布有 2 条成绩记录,含 2 条精确值(可含历史记录)
- OfficeQA · Pro 133-question subset本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- SingleCellBench · LatchBio Bioinformatics single-cell RNA sequencing analysis evaluation本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- Protein Design Library Ranking · Prioritization of protein designs for experimental testing本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- Protocol Understanding · V2; Benchling-created evaluation using real laboratory protocols and applied questions; task count unspecified本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)