Claude Opus 5.5

Anthropic·7 个数据来源·更新于 2026-11-10

上下文窗口1M厂商官网
最大输出128K厂商官网
输入 / 百万 Token$4厂商官网
输出 / 百万 Token$20厂商官网

评测表现

只在同一来源、同一口径下比较。切换来源可查看不同测试结果。

6 个评测来源

当前配置:各基准设置见下表

采集于 2026-11-10查看原始页面

综合分数和同榜图表来自 LLM Stats 榜单(采集于 2026-11-10);下方逐项成绩来自模型页。榜单出处

LLM Stats · LLM Stats Score
58.9原榜第 3 名

同榜模型表现

LLM Stats Score · 同一来源与榜单口径,分数越高越好

7 个配置
所选配置其他配置
查看完整对比数据
模型与配置LLM Stats Score每任务成本
Claude Fable 5.261.3未公布
Claude Mythos 5.259.6未公布
Claude Opus 5.5 · 当前模型58.9未公布
Gemini 4 Carbon57.5未公布
Claude Sonnet 5.557.2未公布
GPT-6 Astra56.8未公布
Kimi K3.1 Pro55.1未公布

不同来源的分数不能直接相加或横向比较;评测任务成本不是 API Token 单价。

逐项基准成绩

32 项已收录成绩 · 保留原始单位和测试条件

AA-Briefcase v1.1厂商自报 · 越高越好
1,822分

System Card Table 8.1.A. AA-Briefcase v1.1 Elo at max effort (max_score 3000).

成绩出处
ArXivMath厂商自报 · 越高越好
91.2%

System Card §8.9. ArXivMath August 2026 (57 problems); without tools; max effort; averaged over four attempts per problem. Evaluated internally without safeguards classifiers.

成绩出处
AutomationBench厂商自报 · 越高越好
40%

Opus 5.5 with production safeguards enabled. Zapier AutomationBench; runs without fallback models, so safeguard interventions counted as failures. Adaptive thinking at max effort.

成绩出处
BenchCAD厂商自报 · 越高越好
73%

System Card §8.13.2. BenchCAD Vision2Code 1k subset; voxel IoU without tools; adaptive thinking at max effort; averaged over five runs.

成绩出处
BenchCAD (with Python tool)厂商自报 · 越高越好
96.2%

System Card §8.13.2. BenchCAD Vision2Code 1k subset; voxel IoU with tools; adaptive thinking at max effort; averaged over five runs.

成绩出处
BioMysteryBench厂商自报 · 越高越好
89.3%

System Card §8.17.1. BioMysteryBench Human Solvable subset 89.3%; adaptive thinking at max effort; bash/file tools with package allow-list.

成绩出处
Chartography厂商自报 · 越高越好
89%

Opus 5.5 with production safeguards enabled. Chartography with tools; adaptive thinking at max effort.

成绩出处
CursorBench 4.0厂商自报 · 越高越好
57.8%

Opus 5.5 with production safeguards enabled. CursorBench 4.0; adaptive thinking at max effort.

成绩出处
DeepSWE 1.1厂商自报 · 越高越好
74.2%

System Card §8.3. DeepSWE v1.1; 5-trial average. Adaptive thinking at max effort.

成绩出处
FrontierCode 1.1厂商自报 · 越高越好
54.4%

Opus 5.5 with production safeguards enabled. FrontierCode v1.1 Main subset; adaptive thinking at max effort.

成绩出处
FrontierSWE V2厂商自报 · 越高越好
62.3%

System Card §8.7. FrontierSWE v2; Proximal harness; max effort; 5 trials per task; mean across trials.

成绩出处
GDPval-AA 2.1厂商自报 · 越高越好
1,846分

Opus 5.5 with production safeguards enabled. GDPval-AA v2.1 Elo (max_score 3000); adaptive thinking at max effort.

成绩出处
Global-MMLU厂商自报 · 越高越好
94.3%

System Card §8.16.1. GMMLU average accuracy 94.3% across 42 languages; adaptive thinking at max effort; single trial; no tools.

成绩出处
HealthBench厂商自报 · 越高越好
60.6%

System Card §8.15.1. HealthBench length-adjusted score 60.6% (penalizes verbose responses); adaptive thinking at max effort; 5-trial average. Prefer length-adjusted over raw 68.1% to match other catalog models and avoid duplicate benchmark_id records.

成绩出处
HealthBench Professional厂商自报 · 越高越好
65.6%

System Card Table 8.1.A length-adjusted score 65.6% (prefer Table 8.1.A over §8.15.2 raw 77.1%). Adaptive thinking at max effort; 5-trial average; safety classifiers enabled with refusal fallback to Claude Opus 5. Length-adjusted per HealthBench Professional paper method.

成绩出处
Humanity's Last Exam (no tools, text-only)厂商自报 · 越高越好
64.4%

System Card Table 8.1.A / §8.11.1. HLE no tools (reasoning-only); adaptive thinking at max effort. Alongside with-tools 67.7% already cataloged from the announcement table.

成绩出处
Humanity's Last Exam (with tools, text-only)厂商自报 · 越高越好
67.7%

Opus 5.5 with production safeguards enabled. Humanity's Last Exam with tools; adaptive thinking at max effort.

成绩出处
LatchBio SingleCellBench厂商自报 · 越高越好
61.2%

System Card §8.17.2. LatchBio SingleCellBench 61.2%; adaptive thinking at max effort; bash/file tools.

成绩出处
LatchBio SpatialBench Verified厂商自报 · 越高越好
72%

System Card §8.17.2. LatchBio SpatialBench Verified 72.0%; adaptive thinking at max effort; bash/file tools.

成绩出处
Legal Agent Benchmark厂商自报 · 越高越好
8.3%

System Card §8.14.2. Legal Agent Benchmark held-out set; all-pass rate 8.3% at max effort (AA harness). Mean criterion-pass rate 91.2% noted in card but not stored as a separate catalog metric (all-pass is the standard LAB reporting id).

成绩出处
LifeSci Diamond (2026-11)来源汇总 · 越高越好
3.6%

Strict pass rate on 55 regulatory-affairs tasks. Plain API via Vercel AI Gateway with a web_search tool (Exa), provider default settings, one answer per task, graded by GPT-6.1 Sol at medium reasoning effort (Arca, 4 Nov 2026 edition).

成绩出处
MILU厂商自报 · 越高越好
93.1%

System Card §8.16.2. MILU average accuracy 93.1% across 11 languages; adaptive thinking at max effort; averaged over 5 trials; no tools.

成绩出处
OfficeQA厂商自报 · 越高越好
78.9%

System Card §8.14.1. OfficeQA full set; max effort; mean of five runs; agentic harness with extracted-text documents and code-execution tools.

成绩出处
OfficeQA Pro厂商自报 · 越高越好
67.7%

System Card §8.14.1. OfficeQA Pro (133-question subset); max effort; mean of five runs.

成绩出处
OSWorld 2.0厂商自报 · 越高越好
81.8%

Opus 5.5 with production safeguards enabled. OSWorld 2.0 partial score (announcement reports partial, not strict); adaptive thinking at max effort.

成绩出处
Program Bench厂商自报 · 越高越好
91.2%

System Card §8.10.1. ProgramBench 166 golden tasks; mini-swe-agent harness; no 6-hour time limit; hidden test pass rate against tests the reference binary passes.

成绩出处
SWE-bench Multilingual厂商自报 · 越高越好
93.9%

System Card Table 8.1.A / §8.2. Adaptive thinking at max effort; 5-trial average. 300 problems across nine programming languages.

成绩出处
SWE-Bench Multimodal厂商自报 · 越高越好
61.4%

System Card Table 8.1.A / §8.2. Adaptive thinking at max effort; 5-trial average. Visual context (screenshots and design mockups).

成绩出处
SWE-Bench Pro厂商自报 · 越高越好
89.9%

System Card Table 8.1.A / §8.2. Adaptive thinking at max effort; 5-trial average. Production safeguards as in card capability summary.

成绩出处
Terminal-Bench 4.0厂商自报 · 越高越好
66.4%

Opus 5.5 with production safeguards enabled. Terminal-Bench 4.0 accuracy 66.4% at xhigh effort (Claude Code harness). Unless otherwise noted, other Opus 5.5 results on this announcement table use adaptive thinking at max effort; TB4 is explicitly reported at xhigh.

成绩出处
Terminal-Bench-Science 0.1厂商自报 · 越高越好
58.7%

Opus 5.5 with production safeguards enabled. Terminal-Bench-Science 0.1; adaptive thinking at max effort.

成绩出处
Toolathlon-Verified厂商自报 · 越高越好
77.8%

System Card §8.14.5. Toolathlon Verified Pass@1 77.8% (3-trial average across 108 tasks). Adaptive thinking at max effort; safety/sandbox stops counted as failures.

成绩出处

技术规格

只展示有可靠来源的资料;优先采用厂商官网与官方模型仓库。

发布日期
2026-09-22厂商官网
知识截止
2026-06厂商官网
上下文窗口
1M Token厂商官网
最大输入
1M TokenLLM Stats
最大输出
128K Token厂商官网
输入模态
文本、图像厂商官网
输出模态
文本厂商官网
开放权重
否Artificial Analysis
推理模式
支持厂商官网
许可证
ProprietaryLLM Stats

价格与用量

美元 / 百万 Token。不同服务商或测试配置的报价分别列出。

模型 API 价格,单位为美元每百万 Token
来源 / 服务商输入输出缓存读取
厂商官网 · Claude Opus 5.5$4$20$0.2
Anthropic$4$20$0.2

估算一次用量

按表格第一条报价计算,普通文本、无缓存。

预计费用$6
不含工具、图片、推理额外计费或阶梯价格;以服务商实际账单为准。

每个数字,都有出处

同名模型通过开发机构和明确版本关联。预览版、日期版本和不同规模模型分别建档。

厂商官网

厂商官方文档 · 基础规格与标准 API 报价

1 条记录最近采集 2026-11-10

Artificial Analysis

公开评测数据;保留来源原始口径

10 条记录最近采集 2026-11-10

LLM Stats

公开模型页与公开榜单;自报成绩单独标识

2 条记录最近采集 2026-11-10

BenchLM

公开评测数据;保留来源原始口径

1 条记录最近采集 2026-11-10

Arena

Arena 官方公开数据集 · CC BY 4.0

4 条记录最近采集 2026-11-10

LiveBench

公开评测数据;保留来源原始口径

1 条记录最近采集 2026-11-10

OpenRouter

公开模型目录与 API 报价

1 条记录最近采集 2026-11-10
查看全部配置与采集记录
来源 / 配置采集时间原始数据
Artificial AnalysisClaude Opus 5.5 (max)SHA-256 c969b09538b1254d…2026-11-10T14:08:35Z查看来源
Artificial AnalysisClaude Opus 5.5 (xhigh)SHA-256 c969b09538b1254d…2026-11-10T14:08:35Z查看来源
Artificial AnalysisClaude Opus 5.5 (high)SHA-256 c969b09538b1254d…2026-11-10T14:08:35Z查看来源
Artificial AnalysisClaude Opus 5.5 (medium)SHA-256 c969b09538b1254d…2026-11-10T14:08:35Z查看来源
Artificial AnalysisClaude Opus 5.5 (low)SHA-256 c969b09538b1254d…2026-11-10T14:08:35Z查看来源
Artificial AnalysisClaude Opus 5.5 (Max, Default Fallback)SHA-256 d88cf30c17a50945…2026-11-10T13:51:48Z查看来源
Artificial AnalysisClaude Opus 5.5 (High, Default Fallback)SHA-256 d88cf30c17a50945…2026-11-10T13:51:48Z查看来源
Artificial AnalysisClaude Opus 5.5 (Low, Default Fallback)SHA-256 d88cf30c17a50945…2026-11-10T13:51:48Z查看来源
Artificial AnalysisClaude Opus 5.5 (Medium, Default Fallback)SHA-256 d88cf30c17a50945…2026-11-10T13:51:48Z查看来源
Artificial AnalysisClaude Opus 5.5 (Xhigh, Default Fallback)SHA-256 d88cf30c17a50945…2026-11-10T13:51:48Z查看来源
LLM StatsClaude Opus 5.52026-11-10T14:08:28Z查看来源
LLM StatsClaude Opus 5.5SHA-256 ad11dc6795205cb2…2026-11-10T13:52:11Z查看来源
BenchLMClaude Opus 5.52026-11-10查看来源
ArenaClaude Opus 5.5 (Max)2026-11-10T14:07:52Z查看来源
ArenaClaude Opus 5.5 (Max)2026-11-10T14:07:52Z查看来源
ArenaClaude Opus 5.5 (High)2026-11-10T14:07:52Z查看来源
ArenaClaude Opus 5.5 (High)2026-11-10T14:07:52Z查看来源
LiveBenchClaude Opus 5.52026-11-10T14:08:34Z查看来源
OpenRouterClaude Opus 5.5SHA-256 63cbc45064d84060…2026-11-10T13:51:49Z查看来源
厂商官网Claude Opus 5.5SHA-256 1b2bed080024e073…2026-11-10T14:00:03Z查看来源
继续浏览模型排行榜