所有发布•

22 个模型

Meta 模型:智能、性能与价格

Artificial Analysis 已对 Meta 的 22 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 Spark 1.3 (max)(48)。
  • 输出速度方面,最快的模型是 Muse Spark 1.3 (xhigh)(221 token/秒)。
  • 延迟方面,Llama 4 Scout(0.84 秒) 的首个答案 token 等待时间最短。
  • 价格方面,Muse Glimmer (high)($0.06) 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)

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

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

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

Meta 的所有发布

更多详情

权重
服务商基准测试
Muse Spark 1.3 (max)
Meta 标志Meta
48
-
1M
US$0.8
203
不可用
Meta
Muse Spark 1.3 (xhigh)
Meta 标志Meta
45
-
1M
US$0.8
221
不可用
Meta
Muse Spark 1.2 (xhigh)
Meta 标志Meta
40
-
1M
US$0.8
234
不可用
Meta
Muse Spark 1.1 (xhigh)
Meta 标志Meta
34
-
1M
US$0.8
-
不可用
Meta
Muse Spark
Meta 标志Meta
31
-
262k
-
-
不可用
-
Muse Glimmer (high)
Meta 标志Meta
17
30B
131k
US$0.2
122
Together AIDeepInfraSystalyzeFireworks
Llama 4 Maverick
Meta 标志Meta
10
402B
推理时启用 17B 个参数
1M
US$0.3
110
NovitaMicrosoft AzureAmazon Bedrock
+3
Llama 4 Scout
Meta 标志Meta
8
109B
推理时启用 17B 个参数
10M
US$0.2
107
DeepInfraMicrosoft AzureGoogle
+3
Llama 3.3 Instruct 70B
Meta 标志Meta
8
70B
128k
US$0.7
90
FireworksGoogleGroq
+10
Llama 3.1 Instruct 405B
Meta 标志Meta
7
405B
128k
-
-
-
Llama 3.1 Instruct 8B
Meta 标志Meta
7
8B
128k
US$0.0
136
GroqNovitaCoreWeave
+3
Llama 3.1 Instruct 70B
Meta 标志Meta
7
70B
128k
US$0.6
52
Amazon BedrockDeepInfra
Llama 3.2 Instruct 90B (Vision)
Meta 标志Meta
6
90B
128k
-
-
-
Llama 2 Chat 7B
Meta 标志Meta
6
7B
4k
US$0.1
-
Replicate
Llama 3.2 Instruct 3B
Meta 标志Meta
6
3B
128k
-
-
-
Llama 3 Instruct 70B
Meta 标志Meta
5
70B
8k
US$0.9
-
NovitaAmazon BedrockReplicate
Llama 3.2 Instruct 11B (Vision)
Meta 标志Meta
5
11B
128k
US$0.3
17
DeepInfra
Llama 2 Chat 70B
Meta 标志Meta
5
70B
4k
-
-
-
Llama 2 Chat 13B
Meta 标志Meta
5
13B
4k
-
-
-
Llama 65B
Meta 标志Meta
5
65B
2k
-
-
-
Llama 3.2 Instruct 1B
Meta 标志Meta
5
1B
128k
-
-
-
Llama 3 Instruct 8B
Meta 标志Meta
5
8B
8k
US$0.1
-
NovitaAmazon BedrockReplicateDeepInfra