Claude Sonnet 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$2厂商官网
输出 / 百万 Token$10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
57.2原榜第 5 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 Mythos 5.259.6未公布
Claude Opus 5.558.9未公布
Gemini 4 Carbon57.5未公布
Claude Sonnet 5.5 · 当前模型57.2未公布
GPT-6 Astra56.8未公布
Kimi K3.1 Pro55.1未公布
Claude Mythos Preview53.9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

47 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
1,811分

Announcement + System Card Table 8.1.A. AA-Briefcase v1.1 Elo (max_score 3000). Same Artificial Analysis pre-release structured-output bug caveat as GDPval-AA.

成绩出处
ArXivMath厂商自报 · 越高越好
86.8%

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
ArXivMath (with tools)厂商自报 · 越高越好
95.2%

System Card §8.9. ArXivMath August 2026 (57 problems); with tools (code-execution sandbox, no internet); max effort; averaged over four attempts per problem.

成绩出处
AutomationBench厂商自报 · 越高越好
44.7%

System Card Table 8.1.A / §8.14.6. Zapier AutomationBench 44.7% at max effort with API default fallbacks enabled. Adaptive thinking at max effort.

成绩出处
BenchCAD厂商自报 · 越高越好
74.7%

System Card §8.13.2. BenchCAD Vision2Code 1k subset; voxel IoU 0.747 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
96.3%

System Card §8.13.2. BenchCAD Vision2Code 1k subset; voxel IoU 0.963 with tools; adaptive thinking at max effort; averaged over five runs.

成绩出处
Biomedical image analysis厂商自报 · 越高越好
72.2%

System Card §8.17.7. Biomedical image analysis 72.2%; 1 attempt per problem; adaptive thinking at max effort.

成绩出处
BioMysteryBench厂商自报 · 越高越好
89.2%

System Card §8.17.1. BioMysteryBench Human Solvable subset 89.2%; adaptive thinking at max effort; bash/file tools with package allow-list. (RSP summary rounded to 0.89; §8.17.1 is authoritative.)

成绩出处
BioMysteryBench (Human Difficult)厂商自报 · 越高越好
44.7%

System Card §8.17.1. BioMysteryBench Human Difficult subset 44.7%; adaptive thinking at max effort; bash/file tools with package allow-list. (RSP summary rounded to 0.45; §8.17.1 is authoritative.)

成绩出处
Chartography厂商自报 · 越高越好
90.2%

System Card §8.13.1. Chartography with tools 90.2%; adaptive thinking at max effort; container with image file, standard libraries, and image cropping tool.

成绩出处
Chartography (no tools)厂商自报 · 越高越好
61.6%

Announcement + System Card §8.13.1. Chartography without tools 61.6%; adaptive thinking at max effort.

成绩出处
CursorBench 4.0厂商自报 · 越高越好
55.5%

Announcement table + System Card §8.8. CursorBench 4.0 at max effort 55.5% (independently measured by Cursor in its production harness). Also reported: xhigh 53.1%, high 47.8%, medium 39.2%.

成绩出处
DeepSWE 1.1厂商自报 · 越高越好
71%

System Card §8.3. DeepSWE v1.1; 5-trial average 71.0%. Adaptive thinking at max effort.

成绩出处
De novo protein binder design厂商自报 · 越高越好
82.3%

System Card §8.17.6. De novo protein binder design 82.3%; 15 targets, 30 miniprotein binders each, 24h wall-clock budget; adaptive thinking at max effort.

成绩出处
FrontierCode 1.1厂商自报 · 越高越好
52.1%

Announcement + System Card §8.4 / Table 8.1.A. FrontierCode v1.1 Main. Catalog stores Xhigh 52.1% as the fair headline (Table 8.1.A max-effort Main is 46.2%). Anthropic notes Max is lower due to Claude Code code-review subagent timeouts / out-of-scope edits penalized by mergeability grading. Extended Xhigh 64.4% stored separately.

成绩出处
FrontierCode 1.1 (Extended)厂商自报 · 越高越好
64.4%

System Card §8.4. FrontierCode v1.1 Extended at Xhigh effort 64.4% (max effort Extended 59.1%). Same mergeability grading caveats as Main.

成绩出处
FrontierSWE V2厂商自报 · 越高越好
61.9%

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
1,844分

Announcement + System Card Table 8.1.A. GDPval-AA v2.1 Elo (max_score 3000). Artificial Analysis evaluated a pre-release Claude Platform deployment with a structured-output bug later fixed; Anthropic expects any impact to be small and to understate performance.

成绩出处
Global-MMLU厂商自报 · 越高越好
92.1%

System Card §8.16.1. GMMLU average accuracy 92.1% 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
65.4%

System Card §8.15.4. HealthBench length-adjusted scores across all five effort levels sit in 64.7–65.4%; store the published band max 65.4% to match the catalog convention (length-adjusted on healthbench). Raw 69.4% at max effort (§8.15.1) is stored separately as healthbench-raw.

成绩出处
HealthBench Professional厂商自报 · 越高越好
69.2%

System Card Table 8.1.A length-adjusted score 69.2% at max effort. Raw (pre-length-adjustment) 77.1% is stored separately as healthbench-professional-raw (§8.15.2). Adaptive thinking at max effort. Length-adjusted per HealthBench Professional paper method.

成绩出处
HealthBench Professional (raw)厂商自报 · 越高越好
77.1%

System Card §8.15.2. HealthBench Professional raw (before length adjustment) 77.1% at max effort; level with Opus 5.5 raw. Length-adjusted 69.2% is stored as healthbench-professional (Table 8.1.A).

成绩出处
HealthBench (raw)厂商自报 · 越高越好
69.4%

System Card §8.15.1. HealthBench raw (before length adjustment) 69.4% at max effort (slightly ahead of Opus 5.5 raw 68.1%). Length-adjusted band max 65.4% is stored as healthbench (§8.15.4).

成绩出处
Humanity's Last Exam (no tools, text-only)厂商自报 · 越高越好
56.9%

System Card Table 8.1.A / §8.11.1. HLE no tools (reasoning-only); adaptive thinking at max effort.

成绩出处
Humanity's Last Exam (with tools)厂商自报 · 越高越好
64.5%

Announcement + System Card Table 8.1.A / §8.11.1. HLE with tools (web search, web fetch, programmatic tool calling, code execution); adaptive thinking at max effort.

成绩出处
LatchBio SingleCellBench厂商自报 · 越高越好
59.1%

System Card §8.17.2. LatchBio SingleCellBench 59.1%; adaptive thinking at max effort; bash/file tools.

成绩出处
LatchBio SpatialBench Verified厂商自报 · 越高越好
72.5%

System Card §8.17.2. LatchBio SpatialBench Verified 72.5%; adaptive thinking at max effort; bash/file tools.

成绩出处
Legal Agent Benchmark厂商自报 · 越高越好
11.7%

System Card §8.14.2. Legal Agent Benchmark held-out set; all-pass rate 11.7% at high effort (AA harness). Mean criterion-pass rate 92.1% noted in card but not stored as a separate catalog metric (all-pass is the standard LAB reporting id). At max effort: 10.0% all-pass / 93.1% mean criterion-pass.

成绩出处
Medicinal Chemistry (ADME)厂商自报 · 越高越好
65.3%

System Card §8.17.4. Medicinal Chemistry ADME 65.3% (504 questions); adaptive thinking at max effort.

成绩出处
MILU厂商自报 · 越高越好
91.6%

System Card §8.16.2. MILU average accuracy 91.6% across 11 languages; adaptive thinking at max effort; averaged over 5 trials; no tools.

成绩出处
Morphology-to-molecule matching厂商自报 · 越高越好
25%

System Card §8.17.3. Axiom Bio morphology-to-molecule matching 25.0%; adaptive thinking at max effort.

成绩出处
OfficeQA厂商自报 · 越高越好
76.9%

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

成绩出处
OfficeQA Pro厂商自报 · 越高越好
65.6%

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

成绩出处
OSWorld 2.1 (partial)厂商自报 · 越高越好
80.1%

Announcement + System Card Table 8.1.A / §8.13.3. OSWorld 2.1 partial-credit score 80.1% (Pass@1, 5-run average) at max effort. Not OSWorld 2.0.

成绩出处
OSWorld 2.1 (strict)厂商自报 · 越高越好
43.5%

System Card §8.13.3. OSWorld 2.1 strict pass rate 43.5% (every checkpoint satisfied; Pass@1, 5-run average) at max effort. Not OSWorld 2.0.

成绩出处
PhysicianBench厂商自报 · 越高越好
63.2%

System Card §8.15.3. PhysicianBench 100 physician EHR tasks; 63.2% pass rate at max effort. Safety classifiers enabled; graded with Claude Opus 5.

成绩出处
Program Bench厂商自报 · 越高越好
79.7%

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
Protein Design — Library Ranking厂商自报 · 越高越好
54.8%

System Card §8.17.5. Protein Design Library Ranking 54.8%; 3 attempts per problem; adaptive thinking at max effort.

成绩出处
Protein Design — Sequence Generation厂商自报 · 越高越好
51%

System Card §8.17.5. Protein Design Sequence Generation 51.0%; 1 attempt per problem; adaptive thinking at max effort.

成绩出处
Protocols Troubleshooting厂商自报 · 越高越好
67.3%

System Card §8.17.8. Protocols Troubleshooting 67.3%; adaptive thinking at max effort.

成绩出处
Protocols Understanding (V2)厂商自报 · 越高越好
66.6%

System Card §8.17.8. Protocols Understanding (V2) (Benchling) 66.6%; adaptive thinking at max effort.

成绩出处
SWE-bench Multilingual厂商自报 · 越高越好
90.3%

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
54.3%

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
81.3%

System Card Table 8.1.A / §8.2. Adaptive thinking at max effort; 5-trial average.

成绩出处
Terminal-Bench 4.0厂商自报 · 越高越好
70.6%

Announcement table + System Card §8.5. Terminal-Bench 4.0 accuracy 70.6% with production safeguards enabled (Claude Code --bare, max thinking effort; 5-trial average). Safeguard-flagged requests used the default server-side fallback (1.2% of requests).

成绩出处
Terminal-Bench-Science 0.1厂商自报 · 越高越好
59.9%

System Card §8.6. Terminal-Bench-Science 0.1; 59.9% with safeguards enabled (no fallbacks fired). Claude Code --bare, max thinking 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 (0.6% of trials).

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
2026-09-28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 Sonnet 5.5$2$10$0.1
Anthropic$2$10$0.1

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$3
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

5 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 Sonnet 5.5 (max)SHA-256 c969b09538b1254d…2026-11-10T14:08:35Z查看来源
Artificial AnalysisClaude Sonnet 5.5 (xhigh)SHA-256 c969b09538b1254d…2026-11-10T14:08:35Z查看来源
Artificial AnalysisClaude Sonnet 5.5 (high)SHA-256 c969b09538b1254d…2026-11-10T14:08:35Z查看来源
Artificial AnalysisClaude Sonnet 5.5 (medium)SHA-256 c969b09538b1254d…2026-11-10T14:08:35Z查看来源
Artificial AnalysisClaude Sonnet 5.5 (low)SHA-256 c969b09538b1254d…2026-11-10T14:08:35Z查看来源
Artificial AnalysisClaude Sonnet 5.5 (Max, Default Fallback)SHA-256 d88cf30c17a50945…2026-11-10T13:51:48Z查看来源
Artificial AnalysisClaude Sonnet 5.5 (High, Default Fallback)SHA-256 d88cf30c17a50945…2026-11-10T13:51:48Z查看来源
Artificial AnalysisClaude Sonnet 5.5 (Low, Default Fallback)SHA-256 d88cf30c17a50945…2026-11-10T13:51:48Z查看来源
Artificial AnalysisClaude Sonnet 5.5 (Medium, Default Fallback)SHA-256 d88cf30c17a50945…2026-11-10T13:51:48Z查看来源
Artificial AnalysisClaude Sonnet 5.5 (Xhigh, Default Fallback)SHA-256 d88cf30c17a50945…2026-11-10T13:51:48Z查看来源
LLM StatsClaude Sonnet 5.52026-11-10T14:08:28Z查看来源
LLM StatsClaude Sonnet 5.5SHA-256 a07313d2503bf2d8…2026-11-10T13:52:10Z查看来源
BenchLMClaude Sonnet 5.52026-11-10查看来源
ArenaClaude Sonnet 5.5 (xHigh)2026-11-10T14:07:52Z查看来源
ArenaClaude Sonnet 5.5 (Max)2026-11-10T14:07:52Z查看来源
ArenaClaude Sonnet 5.5 (High)2026-11-10T14:07:52Z查看来源
ArenaClaude Sonnet 5.5 (xHigh)2026-11-10T14:07:52Z查看来源
ArenaClaude Sonnet 5.5 (xHigh)2026-11-10T14:07:52Z查看来源
LiveBenchClaude Sonnet 5.52026-11-10T14:08:34Z查看来源
OpenRouterClaude Sonnet 5.5SHA-256 63cbc45064d84060…2026-11-10T13:51:49Z查看来源
厂商官网Claude Sonnet 5.5SHA-256 7b1aa8967c22924f…2026-11-10T14:06:44Z查看来源
继续浏览模型排行榜