53 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

Claude Opus 5.5 (max with fallback)

Claude Opus 5.5 (xhigh with fallback)

Claude Opus 5.5 (high with fallback)

Claude Fable 5.1 (max with fallback)

Claude Fable 5.1 (xhigh with fallback)

Artificial Analysis Intelligence Index

速度

Claude Opus 5.5 (max with fallback)

95 Token/秒

Claude Opus 5.5 (xhigh with fallback)

88 Token/秒

Claude 4.5 Haiku

82 Token/秒

Claude Opus 5.5 (medium with fallback)

82 Token/秒

Claude 4.5 Haiku (Non-reasoning)

81 Token/秒

输出速度

成本

Claude 4.5 Haiku

$0.28

Claude Sonnet 5 (low)

$0.51

Claude Opus 5.5 (low with fallback)

$0.55

Claude Sonnet 5 (medium)

$1.00

Claude Opus 5.5 (medium with fallback)

$1.34

每项 Intelligence Index 任务

Artificial Analysis 已对 Anthropic 的 53 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 (Adaptive Reasoning, Max Effort, Default Fallback)（58）。
输出速度方面，最快的模型是 Claude Opus 5.5 (Adaptive Reasoning, Max Effort, Default Fallback)（95 token/秒）。
延迟方面，Claude 4.5 Haiku (Non-reasoning)（0.68 秒）的首个答案 token 等待时间最短。
价格方面，Claude 4.5 Haiku (Reasoning)（$0.28）的单任务成本最低。不同模型的价格差异最高可达 28 倍。

智能

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.3.2 incorporates 10 evaluations: AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1

Estimate (independent evaluation forthcoming)

Artificial Analysis Intelligence Index v4.3.2 includes: AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Intelligence Index vs. Cost per Intelligence Index Task

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

Cost per Intelligence Index Task

Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better

速度与延迟

Output Speed

Output tokens per second · Higher is better

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Figures represent performance of the model's first-party API or the median across providers where a first-party API is not available.

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 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better

Strategy & Ops Index

Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better

Legal Index

Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AA-LCR v1.1, GDP.pdf, AutomationBench-AA · Higher is better

Healthcare & Medical Index

Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, MLCR-AA, Humanity's Last Exam, AutomationBench-AA · Higher is better

Engineering Index

Incorporates 6 evaluations: AA-Omniscience, Humanity's Last Exam, CritPt, GDPval-AA v2.1, AA-Briefcase v1.1, Terminal-Bench 4.0 · Higher is better

Economics Index

Incorporates 5 evaluations: AA-Omniscience, Humanity's Last Exam, GDPval-AA v2.1, AA-Briefcase v1.1, AA-LCR v1.1 · 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 (Adaptive Reasoning, Max Effort, Default Fallback)	Anthropic	58	-	1M	US$2.9	95	不可用		查看
Claude Opus 5.5 (Adaptive Reasoning, Xhigh Effort, Default Fallback)	Anthropic	56	-	1M	US$2.9	88	不可用		查看
Claude Opus 5.5 (Adaptive Reasoning, High Effort, Default Fallback)	Anthropic	54	-	1M	US$2.9	81	不可用		查看
Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)	Anthropic	53	-	1M	US$7.2	70	不可用		查看
Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)	Anthropic	53	-	1M	US$7.2	66	不可用		查看
Claude Opus 5.5 (Adaptive Reasoning, Medium Effort, Default Fallback)	Anthropic	51	-	1M	US$2.9	82	不可用		查看
Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)	Anthropic	51	-	1M	US$7.2	57	不可用		查看
Claude Opus 5 (Adaptive Reasoning, Max Effort)	Anthropic	51	-	1M	US$3.9	60	不可用		查看
Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)	Anthropic	50	-	1M	US$3.9	59	不可用		查看
Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)	Anthropic	50	-	1M	US$7.7	64	不可用		查看
Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback)	Anthropic	49	-	1M	US$7.2	58	不可用		查看
Claude Opus 5 (Adaptive Reasoning, High Effort)	Anthropic	48	-	1M	US$3.9	59	不可用		查看
Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback)	Anthropic	47	-	1M	US$7.2	58	不可用		查看
Claude Opus 5 (Adaptive Reasoning, Medium Effort)	Anthropic	45	-	1M	US$3.9	62	不可用		查看
Claude Opus 5.5 (Adaptive Reasoning, Low Effort, Default Fallback)	Anthropic	42	-	1M	US$2.9	79	不可用		查看
Claude Opus 4.8 (Adaptive Reasoning, Max Effort)	Anthropic	42	-	1M	US$3.9	52	不可用		查看
Claude Opus 4.7 (Adaptive Reasoning, Max Effort)	Anthropic	41	-	1M	US$3.9	52	不可用		查看
Claude Opus 5 (Adaptive Reasoning, Low Effort)	Anthropic	39	-	1M	US$3.9	63	不可用		查看
Claude Sonnet 5 (Adaptive Reasoning, Max Effort)	Anthropic	38	-	1M	US$1.5	75	不可用		查看
Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort)	Anthropic	34	-	1M	US$1.5	69	不可用		查看
Claude Opus 4.6 (Adaptive Reasoning, Max Effort)	Anthropic	32	-	1M	US$3.9	39	不可用		查看
Claude Sonnet 5 (Adaptive Reasoning, High Effort)	Anthropic	32	-	1M	US$1.5	65	不可用		查看
Claude Opus 4.7 (Non-reasoning, High Effort)	Anthropic	31	-	1M	US$3.9	48	不可用		查看
Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)	Anthropic	30	-	1M	US$2.3	48	不可用		查看
Claude Opus 4.5 (Reasoning)	Anthropic	29	-	200k	US$3.9	49	不可用		查看
Claude Sonnet 5 (Adaptive Reasoning, Medium Effort)	Anthropic	28	-	1M	US$1.5	63	不可用		查看
Claude Opus 4.6 (Non-reasoning, High Effort)	Anthropic	26	-	1M	US$3.9	38	不可用		查看
Claude Sonnet 4.6 (Non-reasoning, High Effort)	Anthropic	25	-	1M	US$2.3	42	不可用		查看
Claude Sonnet 5 (Adaptive Reasoning, Low Effort)	Anthropic	24	-	1M	US$1.5	58	不可用		查看
Claude Opus 4.5 (Non-reasoning)	Anthropic	24	-	200k	US$3.9	46	不可用		查看
Claude Sonnet 4.6 (Non-reasoning, Low Effort)	Anthropic	23	-	1M	US$2.3	44	不可用		查看
Claude Sonnet 5 (Non-reasoning, High Effort)	Anthropic	23	-	1M	US$1.5	66	不可用		查看
Claude 4.1 Opus (Reasoning)	Anthropic	23	-	200k	US$11.6	-	不可用		查看
Claude 4.5 Sonnet (Reasoning)	Anthropic	21	-	1M	US$2.3	40	不可用		查看
Claude 4 Opus (Reasoning)	Anthropic	21	-	200k	US$11.6	-	不可用		查看
Claude 4.5 Sonnet (Non-reasoning)	Anthropic	19	-	1M	US$2.3	39	不可用		查看
Claude 4 Sonnet (Reasoning)	Anthropic	19	-	1M	-	-	不可用	-	查看
Claude 4.1 Opus (Non-reasoning)	Anthropic	19	-	200k	US$11.6	-	不可用		查看
Claude 3.7 Sonnet (Reasoning)	Anthropic	18	-	200k	-	-	不可用	-	查看
Claude 4.5 Haiku (Reasoning)	Anthropic	17	-	200k	US$0.8	82	不可用		查看
Claude 4 Opus (Non-reasoning)	Anthropic	17	-	200k	US$11.6	-	不可用		查看
Claude 4 Sonnet (Non-reasoning)	Anthropic	17	-	1M	-	-	不可用	-	查看
Claude 4.5 Haiku (Non-reasoning)	Anthropic	15	-	200k	US$0.8	81	不可用		查看
Claude 3.7 Sonnet (Non-reasoning)	Anthropic	15	-	200k	US$2.3	-	不可用		查看
Claude 3.5 Haiku	Anthropic	9	-	200k	-	-	不可用	-	查看
Claude 3 Opus	Anthropic	9	-	200k	US$11.6	-	不可用		查看
Claude 3.5 Sonnet (Oct '24)	Anthropic	8	-	200k	US$2.3	-	不可用		查看
Claude 3.5 Sonnet (June '24)	Anthropic	7	-	200k	US$2.3	-	不可用		查看
Claude 3 Sonnet	Anthropic	6	-	200k	-	-	不可用	-	查看
Claude 2.1	Anthropic	6	-	200k	-	-	不可用	-	查看
Claude 3 Haiku	Anthropic	6	-	200k	US$0.4	-	不可用		查看
Claude 2.0	Anthropic	6	-	100k	-	-	不可用	-	查看
Claude Instant	Anthropic	5	-	100k	-	-	不可用	-	查看

Anthropic 模型：智能、性能与价格

智能

速度

成本

智能

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

Intelligence Index vs. Cost per Intelligence Index Task

Cost per Intelligence Index Task

Artificial Analysis Intelligence Index

成本

Cost per Intelligence Index Task

Cost per Intelligence Index Task

速度与延迟

Output Speed

Output Speed

Model Performance Representation

能力得分

能力指数

Anthropic 的所有发布

更多详情