26 个模型

Meta 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

智能

Updated

Muse Wonder Full (max)

Muse Wonder (max)

Muse Wonder (high)

Muse Spark Open (xhigh)

Muse Glimmer (high)

Artificial Analysis Intelligence Index

每任务耗时

Muse Glimmer (high)

4.5 分钟

Muse Spark Open (xhigh)

5.8 分钟

Muse Wonder (high)

9.1 分钟

Muse Wonder (max)

13.0 分钟

Llama 3.1 405B

每项 Intelligence Index 任务

成本

Muse Glimmer (high)

$0.16

Muse Spark Open (xhigh)

每项 Intelligence Index 任务

Artificial Analysis 已对 Meta 的 26 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，Meta 得分最高的模型是 Muse Wonder Full (Max)（50）。
速度方面，Muse Glimmer (High)（4.5 分钟）的每任务耗时最短。
延迟方面，Llama 4 Scout（1.13 秒）的首个答案 token 等待时间最短。
价格方面，Muse Glimmer (High)（$0.16）的单任务成本最低。不同模型的价格差异最高可达 43 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

No publicly available API

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

更多详情

								权重		服务商基准测试
Muse Wonder Full (Max)	Meta	50	-	1M	-	-	-	不可用	-	查看
Muse Wonder (Max)	Meta	44	-	1M	$2.94	13.0	123	不可用		查看
Muse Wonder (High)	Meta	41	-	1M	$2.94	9.1	124	不可用		查看
Muse Spark 1.3 (Max)	Meta	37	-	1M	$0.78	12.5	122	不可用		查看
Muse Spark Open (Xhigh)	Meta	25	816B 推理时启用 42B 个参数	1M	$0.78	5.8	191	🤗	+4	查看
Muse Glimmer (High)	Meta	6	30B	131k	$0.21	4.5	95	🤗		查看
Muse Spark 1.2 (Xhigh)	Meta	-	-	1M	$0.78	-	199	不可用		查看
Llama 3.1 Instruct 405B	Meta	-	405B	128k	-	-	-	🤗	-	查看
Llama 3.1 Instruct 70B	Meta	-	70B	128k	$0.56	-	14	🤗		查看
Llama 2 Chat 70B	Meta	-	70B	4k	-	-	-	🤗	-	查看
Llama 3.2 Instruct 11B (Vision)	Meta	-	11B	128k	$0.35	-	20	🤗		查看
Llama 2 Chat 13B	Meta	-	13B	4k	-	-	-	🤗	-	查看
Llama 3.2 Instruct 3B	Meta	-	3B	128k	-	-	-	🤗	-	查看
Llama 3.1 Instruct 8B	Meta	-	8B	128k	$0.038	-	122	🤗	+2	查看
Llama 3.2 Instruct 1B	Meta	-	1B	128k	-	-	-	🤗	-	查看
Llama 3 Instruct 8B	Meta	-	8B	8k	$0.055	-	59	🤗		查看
Llama 4 Maverick	Meta	-	402B 推理时启用 17B 个参数	1M	$0.30	-	67	🤗	+3	查看
Llama 3.3 Instruct 70B	Meta	-	70B	128k	$0.61	-	75	🤗	+6	查看
Llama 3.2 Instruct 90B (Vision)	Meta	-	90B	128k	-	-	-	🤗	-	查看
Llama 3 Instruct 70B	Meta	-	70B	8k	$0.86	-	47	🤗		查看
Llama 4 Scout	Meta	-	109B 推理时启用 17B 个参数	10M	$0.23	-	86	🤗	+2	查看
Muse Spark 1.3 (Xhigh)	Meta	-	-	1M	$0.78	-	238	不可用		查看
Muse Spark 1.1 (Xhigh)	Meta	-	-	1M	$0.78	-	197	不可用		查看
Muse Spark	Meta	-	-	262k	-	-	-	不可用	-	查看
Llama 65B	Meta	-	65B	2k	-	-	-	🤗	-	查看
Llama 2 Chat 7B	Meta	-	7B	4k	-	-	-	🤗	-	查看

Meta 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

Meta 的所有发布

更多详情