63 个模型

Anthropic 模型：智能、性能与价格

Name: Artificial Analysis Intelligence Index
Creator: Artificial Analysis
License: https://artificialanalysis.ai/docs/legal/Terms-of-Use.pdf

Anthropic

智能

Updated

Claude Opus 5.5 (max)

Claude Opus 5.5 (xhigh)

Claude Sonnet 5.5 (max)

Claude Opus 5.5 (high)

Claude Fable 5.1 (xhigh)

Artificial Analysis Intelligence Index

每任务耗时

Claude Haiku 5.5 (low)

2.2 分钟

Claude Sonnet 5.5 (low)

2.7 分钟

Claude Opus 5.5 (low)

3.0 分钟

Claude Sonnet 5.5 (medium)

3.6 分钟

Claude Haiku 5.5 (medium)

4.2 分钟

每项 Intelligence Index 任务

成本

Claude Haiku 5.5 (low)

$0.04

Claude Haiku 5.5 (medium)

$0.09

Claude Haiku 5.5 (high)

$0.16

Claude Haiku 5.5 (xhigh)

$0.25

Claude Haiku 5.5 (max)

$0.41

每项 Intelligence Index 任务

Artificial Analysis 已对 Anthropic 的 63 个模型进行基准测试。下方对这些模型的关键指标进行了比较。

智能方面，Anthropic 得分最高的模型是 Claude Opus 5.5 (Max, Default Fallback)（59）。
速度方面，Claude Haiku 5.5 (Low)（2.2 分钟）的每任务耗时最短。
延迟方面，Claude Sonnet 5.5 (Low, Default Fallback)（3.28 秒）的首个答案 token 等待时间最短。
价格方面，Claude Haiku 5.5 (Low)（$0.04）的单任务成本最低。不同模型的价格差异最高可达 297 倍。

智能Updated

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v5.0.1 incorporates 9 evaluations: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), and Terminal-Bench-Science 0.1

Artificial Analysis Intelligence Index v5.0.1 includes: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), Terminal-Bench-Science 0.1. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Intelligence Index 与每项任务的成本

Artificial Analysis Intelligence Index · Weighted average cost (USD) per Artificial Analysis Intelligence Index task

Most attractive quadrant

Pareto line

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

成本

每项 Intelligence Index 任务的成本

Weighted average cost (USD) per Intelligence Index task · Segmented by token type · Lower is better

速度与延迟

Intelligence Index 每项任务耗时

Output tokens divided by end-to-end output speed (minutes per Intelligence Index task) · Speed at the model's own endpoint or the median across providers · Lower is better

The weighted average time (minutes) per Artificial Analysis Intelligence Index task: output tokens per task divided by output speed, weighted by each benchmark's weight in the Intelligence Index.

Speed and latency metrics average each endpoint's runs over the past 5 days, and the error rate pools them. We run the benchmark every 6 hours, and endpoints of deprecated models every 18 hours.

能力得分

能力指数

衡量模型在特定能力与行业中的表现

Finance & Accounting Index

Incorporates 5 evaluations: AA-Briefcase v1.1, AA-Omniscience v1.1, HLE-Diamond, AutomationBench-AA, GDP.pdf · Higher is better

Strategy & Ops Index

Incorporates 4 evaluations: AutomationBench-AA, AA-Briefcase v1.1, AA-Omniscience v1.1, GDP.pdf · Higher is better

Legal Index

Incorporates 5 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, HLE-Diamond, GDP.pdf, AutomationBench-AA · Higher is better

Healthcare & Medical Index

Incorporates 5 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, MLCR-AA, AutomationBench-AA, HLE-Diamond · Higher is better

Engineering Index

Incorporates 7 evaluations: AA-Omniscience v1.1, CritPt v2 (Hard Subset), Terminal-Bench-Science 0.1, HLE-Diamond, Terminal-Bench 4.0, FrontierCode 2.0, AA-Briefcase v1.1 · Higher is better

Economics Index

Incorporates 4 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, HLE-Diamond, GDP.pdf · Higher is better

Anthropic 的所有发布

更多详情

								权重		服务商基准测试
Claude Opus 5.5 (Max, Default Fallback)	Anthropic	59	-	1M	US$2.9	25.3	114	不可用		查看
Claude Opus 5.5 (Xhigh, Default Fallback)	Anthropic	57	-	1M	US$2.9	16.0	108	不可用		查看
Claude Sonnet 5.5 (Max, Default Fallback)	Anthropic	55	-	1M	US$1.5	31.1	153	不可用		查看
Claude Opus 5.5 (High, Default Fallback)	Anthropic	52	-	1M	US$2.9	9.5	106	不可用		查看
Claude Fable 5.1 (Xhigh, Default Fallback)	Anthropic	50	-	1M	US$7.2	18.5	88	不可用		查看
Claude Sonnet 5.5 (Xhigh, Default Fallback)	Anthropic	50	-	1M	US$1.5	15.2	134	不可用		查看
Claude Fable 5.1 (Max, Default Fallback)	Anthropic	49	-	1M	US$7.2	22.6	87	不可用		查看
Claude Opus 5.5 (Medium, Default Fallback)	Anthropic	48	-	1M	US$2.9	7.0	105	不可用		查看
Claude Fable 5.1 (High, Default Fallback)	Anthropic	47	-	1M	US$7.2	12.7	87	不可用		查看
Claude Opus 5 (Max)	Anthropic	44	-	1M	US$3.9	29.1	68	不可用		查看
Claude Fable 5.1 (Medium, Default Fallback)	Anthropic	43	-	1M	US$7.2	9.3	87	不可用		查看
Claude Sonnet 5.5 (High, Default Fallback)	Anthropic	42	-	1M	US$1.5	7.0	139	不可用		查看
Claude Fable 5.1 (Low, Default Fallback)	Anthropic	39	-	1M	US$7.2	7.2	87	不可用		查看
Claude Haiku 5.5 (Max)	Anthropic	36	-	1M	US$0.1	16.7	225	不可用		查看
Claude Opus 5.5 (Low, Default Fallback)	Anthropic	35	-	1M	US$2.9	3.0	104	不可用		查看
Claude Haiku 5.5 (Xhigh)	Anthropic	35	-	1M	US$0.1	9.8	232	不可用		查看
Claude Sonnet 5.5 (Medium, Default Fallback)	Anthropic	31	-	1M	US$1.5	3.6	143	不可用		查看
Claude Haiku 5.5 (High)	Anthropic	30	-	1M	US$0.1	6.5	226	不可用		查看
Claude Sonnet 5.5 (Low, Default Fallback)	Anthropic	26	-	1M	US$1.5	2.7	131	不可用		查看
Claude Haiku 5.5 (Medium)	Anthropic	25	-	1M	US$0.1	4.2	214	不可用		查看
Claude Haiku 5.5 (Low)	Anthropic	19	-	1M	US$0.1	2.2	216	不可用		查看
Claude 4.5 Haiku (Reasoning)	Anthropic	7	-	200k	US$0.8	4.0	104	不可用		查看
Claude 3.5 Haiku	Anthropic	-	-	200k	-	-	-	不可用	-	查看
Claude 3.5 Sonnet (Oct '24)	Anthropic	-	-	200k	US$2.3	-	-	不可用		查看
Claude Opus 5 (Xhigh)	Anthropic	-	-	1M	US$3.9	-	77	不可用		查看
Claude 3.7 Sonnet (Reasoning)	Anthropic	-	-	200k	-	-	-	不可用	-	查看
Claude Sonnet 5 (Low)	Anthropic	-	-	1M	US$1.5	-	105	不可用		查看
Claude 3 Haiku	Anthropic	-	-	200k	US$0.4	-	-	不可用		查看
Claude Opus 5 (Low)	Anthropic	-	-	1M	US$3.9	-	81	不可用		查看
Claude Sonnet 5 (Max)	Anthropic	-	-	1M	US$1.5	-	105	不可用		查看
Claude Opus 4.5 (Reasoning)	Anthropic	-	-	200k	US$3.9	-	66	不可用		查看
Claude Sonnet 4.6 (Non-reasoning, High)	Anthropic	-	-	1M	US$2.3	-	56	不可用		查看
Claude Opus 4.7 (Non-reasoning, High)	Anthropic	-	-	1M	US$3.9	-	76	不可用		查看
Claude Opus 4.5 (Non-reasoning)	Anthropic	-	-	200k	US$3.9	-	66	不可用		查看
Claude Opus 4.6 (Non-reasoning, High)	Anthropic	-	-	1M	US$3.9	-	52	不可用		查看
Claude 4 Opus (Non-reasoning)	Anthropic	-	-	200k	US$11.6	-	-	不可用		查看
Claude Opus 4.6 (Max)	Anthropic	-	-	1M	US$3.9	-	54	不可用		查看
Claude Opus 5 (High)	Anthropic	-	-	1M	US$3.9	-	80	不可用		查看
Claude 3 Opus	Anthropic	-	-	200k	US$11.6	-	-	不可用		查看
Claude Instant	Anthropic	-	-	100k	-	-	-	不可用	-	查看
Claude 4 Opus (Reasoning)	Anthropic	-	-	200k	US$11.6	-	-	不可用		查看
Claude 4.5 Sonnet (Reasoning)	Anthropic	-	-	1M	US$2.3	-	55	不可用		查看
Claude 4.5 Sonnet (Non-reasoning)	Anthropic	-	-	1M	US$2.3	-	55	不可用		查看
Claude Opus 4.8 (Max)	Anthropic	-	-	1M	US$3.9	-	85	不可用		查看
Claude Sonnet 5 (Xhigh)	Anthropic	-	-	1M	US$1.5	-	105	不可用		查看
Claude 2.1	Anthropic	-	-	200k	-	-	-	不可用	-	查看
Claude 4 Sonnet (Reasoning)	Anthropic	-	-	1M	-	-	-	不可用	-	查看
Claude 3.5 Sonnet (June '24)	Anthropic	-	-	200k	US$2.3	-	-	不可用		查看
Claude 3 Sonnet	Anthropic	-	-	200k	-	-	-	不可用	-	查看
Claude Sonnet 5 (High)	Anthropic	-	-	1M	US$1.5	-	105	不可用		查看
Claude 4.5 Haiku (Non-reasoning)	Anthropic	-	-	200k	US$0.8	-	100	不可用		查看
Claude 4.1 Opus (Reasoning)	Anthropic	-	-	200k	US$11.6	-	-	不可用		查看
Claude Fable 5 (Max, Opus 4.8 Fallback)	Anthropic	-	-	1M	US$7.7	-	90	不可用		查看
Claude 4 Sonnet (Non-reasoning)	Anthropic	-	-	1M	-	-	-	不可用	-	查看
Claude Sonnet 5 (Non-reasoning, High)	Anthropic	-	-	1M	US$1.5	-	103	不可用		查看
Claude 3.7 Sonnet (Non-reasoning)	Anthropic	-	-	200k	US$2.3	-	-	不可用		查看
Claude 2.0	Anthropic	-	-	100k	-	-	-	不可用	-	查看
Claude Sonnet 4.6 (Max)	Anthropic	-	-	1M	US$2.3	-	62	不可用		查看
Claude Opus 4.7 (Max)	Anthropic	-	-	1M	US$3.9	-	81	不可用		查看
Claude Sonnet 5 (Medium)	Anthropic	-	-	1M	US$1.5	-	103	不可用		查看
Claude Sonnet 4.6 (Non-reasoning, Low)	Anthropic	-	-	1M	US$2.3	-	52	不可用		查看
Claude 4.1 Opus (Non-reasoning)	Anthropic	-	-	200k	US$11.6	-	-	不可用		查看
Claude Opus 5 (Medium)	Anthropic	-	-	1M	US$3.9	-	81	不可用		查看

Anthropic 模型：智能、性能与价格

智能

每任务耗时

成本

智能Updated

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

Intelligence Index 与每项任务的成本

Cost per Intelligence Index Task

Artificial Analysis Intelligence Index

成本

每项 Intelligence Index 任务的成本

Cost per Intelligence Index Task

速度与延迟

Intelligence Index 每项任务耗时

Time per Intelligence Index Task

Time Period

能力得分

能力指数

Anthropic 的所有发布

更多详情