Claude Sonnet 5.5
Anthropic·7 个数据来源·更新于 2026-11-10
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。
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
同榜模型表现
LLM Stats Score · 同一来源与榜单口径,分数越高越好
查看完整对比数据
| 模型与配置 | LLM Stats Score | 每任务成本 |
|---|---|---|
| Claude Mythos 5.2 | 59.6 | 未公布 |
| Claude Opus 5.5 | 58.9 | 未公布 |
| Gemini 4 Carbon | 57.5 | 未公布 |
| Claude Sonnet 5.5 · 当前模型 | 57.2 | 未公布 |
| GPT-6 Astra | 56.8 | 未公布 |
| Kimi K3.1 Pro | 55.1 | 未公布 |
| Claude Mythos Preview | 53.9 | 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
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System Card §8.17.7. Biomedical image analysis 72.2%; 1 attempt per problem; adaptive thinking at max effort.
成绩出处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Announcement + System Card §8.13.1. Chartography without tools 61.6%; adaptive thinking at max effort.
成绩出处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System Card §8.3. DeepSWE v1.1; 5-trial average 71.0%. Adaptive thinking at max effort.
成绩出处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System Card §8.7. FrontierSWE v2; Proximal harness; max effort; 5 trials per task; mean across trials.
成绩出处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System Card Table 8.1.A / §8.11.1. HLE no tools (reasoning-only); adaptive thinking at max effort.
成绩出处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System Card §8.17.2. LatchBio SingleCellBench 59.1%; adaptive thinking at max effort; bash/file tools.
成绩出处System Card §8.17.2. LatchBio SpatialBench Verified 72.5%; adaptive thinking at max effort; bash/file tools.
成绩出处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System Card §8.17.4. Medicinal Chemistry ADME 65.3% (504 questions); adaptive thinking at max effort.
成绩出处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System Card §8.17.3. Axiom Bio morphology-to-molecule matching 25.0%; adaptive thinking at max effort.
成绩出处System Card §8.14.1. OfficeQA full set; max effort; agentic harness with extracted-text documents and code-execution tools.
成绩出处System Card §8.14.1. OfficeQA Pro (133-question subset); max effort.
成绩出处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System Card §8.17.5. Protein Design Library Ranking 54.8%; 3 attempts per problem; adaptive thinking at max effort.
成绩出处System Card §8.17.5. Protein Design Sequence Generation 51.0%; 1 attempt per problem; adaptive thinking at max effort.
成绩出处System Card §8.17.8. Protocols Troubleshooting 67.3%; adaptive thinking at max effort.
成绩出处System Card §8.17.8. Protocols Understanding (V2) (Benchling) 66.6%; adaptive thinking at max effort.
成绩出处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System Card Table 8.1.A / §8.2. Adaptive thinking at max effort; 5-trial average.
成绩出处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。
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。
| 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 |
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
Artificial Analysis
公开评测数据;保留来源原始口径
LLM Stats
公开模型页与公开榜单;自报成绩单独标识
BenchLM
公开评测数据;保留来源原始口径
Arena
Arena 官方公开数据集 · CC BY 4.0
LiveBench
公开评测数据;保留来源原始口径
OpenRouter
公开模型目录与 API 报价
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 5.5 | 2026-11-10T14:08:28Z | 查看来源 |
| LLM StatsClaude Sonnet 5.5SHA-256 a07313d2503bf2d8… | 2026-11-10T13:52:10Z | 查看来源 |
| BenchLMClaude Sonnet 5.5 | 2026-11-10 | 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 5.5 | 2026-11-10T14:08:34Z | 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 |