69 个模型

Google 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

Google

智能

Updated

Gemini 4 Carbon (high)

Gemini 4 Carbon (medium)

Gemini 4 Carbon (low)

Gemini 4 Argon (high)

Gemini 3.8 Flash (high)

Artificial Analysis Intelligence Index

每任务耗时

Gemini 3.5 Flash-Lite

1.7 分钟

Gemini 3.8 Flash (medium)

13.0 分钟

Gemini 3.8 Flash (high)

14.6 分钟

Gemini 4 Carbon (medium)

24.6 分钟

Gemini 4 Argon (high)

27.7 分钟

每项 Intelligence Index 任务

成本

Gemini 3.5 Flash-Lite

$0.69

Gemini 3.8 Flash (medium)

$6.26

Gemini 4 Carbon (medium)

$6.59

Gemini 4 Carbon (low)

$7.19

Gemini 4 Carbon (high)

$7.76

每项 Intelligence Index 任务

Artificial Analysis 已对 Google 的 69 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，Google 得分最高的模型是 Gemini 4 Carbon (High)（60）。
速度方面，Gemini 3.5 Flash-Lite（1.7 分钟）的每任务耗时最短。
延迟方面，Gemma 4 26B A4B (Non-reasoning)（1.59 秒）的首个答案 token 等待时间最短。
价格方面，Gemini 3.5 Flash-Lite（$0.69）的单任务成本最低。不同模型的价格差异最高可达 14 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

No publicly available API

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

No publicly available API

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

Google 的所有发布

更多详情

								权重		服务商基准测试
Gemini 4 Carbon (High)	Google	60	-	1M	US$2.9	30.8	66	不可用		查看
Gemini 4 Carbon (Medium)	Google	58	-	1M	US$2.9	24.6	70	不可用		查看
Gemini 4 Carbon (Low)	Google	54	-	1M	US$2.9	35.4	41	不可用		查看
Gemini 4 Argon (High)	Google	50	-	1M	US$2.9	27.7	70	不可用		查看
Gemini 3.8 Flash (High)	Google	31	-	1M	US$0.6	14.6	113	不可用		查看
Gemini 3.8 Flash (Medium)	Google	30	-	1M	US$0.6	13.0	105	不可用		查看
Gemini 3.8 Flash (Low)	Google	23	-	1M	US$0.6	-	89	不可用		查看
Gemini 3.5 Flash-Lite	Google	12	-	1M	US$0.3	1.7	291	不可用		查看
Gemini 3.1 Flash-Lite	Google	6	-	1M	US$0.2	0.7	357	不可用		查看
Gemma 4 31B (Reasoning)	Google	4	30.7B	256k	US$0.0	-	30	🤗	+8	查看
Gemini 3.5 Flash (High)	Google	-	-	1M	US$1.3	-	191	不可用		查看
Gemma 4 12B (Non-reasoning)	Google	-	12B	262k	US$0.1	-	62	🤗		查看
Gemini 3.5 Flash (Minimal)	Google	-	-	1M	US$1.3	-	149	不可用		查看
Gemini 2.0 Flash Thinking Experimental (Jan '25)	Google	-	-	1M	-	-	-	不可用	-	查看
Gemma 3 270M	Google	-	0.3B	32k	-	-	-	🤗	-	查看
Gemini 2.5 Pro Preview (May' 25)	Google	-	-	1M	US$1.3	-	-	不可用		查看
Gemini 1.5 Pro (May '24)	Google	-	-	2M	-	-	-	不可用	-	查看
Gemini 2.5 Flash-Lite (Non-reasoning)	Google	-	-	1M	US$0.1	-	274	不可用		查看
Gemini 2.5 Flash (Reasoning)	Google	-	-	1M	US$0.3	-	207	不可用		查看
Gemma 3 4B Instruct	Google	-	4.3B	128k	US$0.0	-	76	🤗		查看
Gemini 2.5 Pro	Google	-	-	1M	US$1.3	-	105	不可用		查看
Gemini 1.5 Pro (Sep '24)	Google	-	-	2M	-	-	-	不可用	-	查看
Gemini 1.0 Ultra	Google	-	-	33k	-	-	-	不可用	-	查看
Gemma 3 27B Instruct	Google	-	27.4B	128k	US$0.0	-	39	🤗	+3	查看
Gemma 3 12B Instruct	Google	-	12.2B	128k	US$0.0	-	52	🤗		查看
Gemini 2.0 Flash-Lite (Preview)	Google	-	-	1M	-	-	-	不可用	-	查看
Gemini 1.5 Flash (Sep '24)	Google	-	-	1M	-	-	-	不可用	-	查看
Gemini 3.5 Flash (Medium)	Google	-	-	1M	US$1.3	-	154	不可用		查看
PALM-2	Google	-	-	8k	-	-	-	不可用	-	查看
Gemma 4 E4B (Non-reasoning)	Google	-	8B 推理时启用 4.5B 个参数	128k	US$0.0	-	52	🤗		查看
Gemini 2.5 Flash Preview (Non-reasoning)	Google	-	-	1M	-	-	-	不可用	-	查看
Gemini 2.5 Pro Preview (Mar' 25)	Google	-	-	1M	-	-	-	不可用	-	查看
Gemini 2.5 Flash Preview (Reasoning)	Google	-	-	1M	-	-	-	不可用	-	查看
Gemini 2.5 Flash (Non-reasoning)	Google	-	-	1M	US$0.3	-	178	不可用		查看
Gemma 4 26B A4B (Reasoning)	Google	-	25.2B 推理时启用 3.8B 个参数	256k	US$0.1	-	69	🤗	+4	查看
Gemma 4 26B A4B (Non-reasoning)	Google	-	25.2B 推理时启用 3.8B 个参数	256k	US$0.1	-	88	🤗	+5	查看
Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)	Google	-	-	1M	US$0.1	-	-	不可用		查看
Gemma 4 E2B (Non-reasoning)	Google	-	5.1B 推理时启用 2.3B 个参数	128k	-	-	-	🤗	-	查看
Gemini 3.6 Flash (High)	Google	-	-	1M	US$0.6	-	188	不可用		查看
Gemini 3 Flash Preview (Non-reasoning)	Google	-	-	1M	US$0.4	-	195	不可用		查看
Gemini 2.0 Flash-Lite (Feb '25)	Google	-	-	1M	-	-	-	不可用	-	查看
Gemini 3 Flash Preview (Reasoning)	Google	-	-	1M	US$0.4	-	206	不可用		查看
Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)	Google	-	-	1M	US$0.1	-	-	不可用		查看
Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)	Google	-	-	1M	-	-	-	不可用	-	查看
Gemini 1.0 Pro	Google	-	-	33k	-	-	-	不可用	-	查看
Gemini 1.5 Flash-8B	Google	-	8B	1M	-	-	-	不可用	-	查看
Gemini 3 Deep Think	Google	-	-	128k	-	-	-	不可用	-	查看
Gemma 3n E4B Instruct	Google	-	8.4B 推理时启用 4B 个参数	32k	-	-	-	🤗	-	查看
Gemma 3n E2B Instruct	Google	-	6.0B 推理时启用 2B 个参数	32k	US$0.0	-	-	🤗		查看
Gemini 1.5 Flash (May '24)	Google	-	-	1M	-	-	-	不可用	-	查看
Gemma 4 E2B (Reasoning)	Google	-	5.1B 推理时启用 2.3B 个参数	128k	-	-	-	🤗	-	查看
Gemini 3.7 Flash (High)	Google	-	-	1M	US$0.6	-	-	不可用	-	查看
Gemini 3 Pro Preview (Low)	Google	-	-	1M	US$1.7	-	-	不可用		查看
Gemini 3.1 Pro Preview	Google	-	-	1M	US$1.7	-	122	不可用		查看
Gemini 2.0 Flash (Feb '25)	Google	-	-	1M	-	-	-	不可用	-	查看
Gemma 3n E4B Instruct Preview (May '25)	Google	-	8.4B 推理时启用 4B 个参数	32k	-	-	-	🤗	-	查看
DiffusionGemma 26B A4B	Google	-	25.2B 推理时启用 3.8B 个参数	256k	-	-	-	🤗	-	查看
Gemini 2.0 Pro Experimental (Feb '25)	Google	-	-	2M	-	-	-	不可用	-	查看
Gemini 2.5 Flash Preview (Sep '25) (Reasoning)	Google	-	-	1M	-	-	-	不可用	-	查看
Gemma 4 31B (Non-reasoning)	Google	-	30.7B	256k	US$0.2	-	51	🤗	+7	查看
Gemini 3 Pro Preview (High)	Google	-	-	1M	US$1.7	-	-	不可用		查看
Gemma 3 1B Instruct	Google	-	1B	32k	US$0.0	-	-	🤗		查看
Gemma 4 E4B (Reasoning)	Google	-	8B 推理时启用 4.5B 个参数	128k	US$0.0	-	55	🤗		查看
Gemini 3.7 Flash (Low)	Google	-	-	1M	-	-	-	不可用	-	查看
Gemini 2.0 Flash Thinking Experimental (Dec '24)	Google	-	-	2M	-	-	-	不可用	-	查看
Gemini 3.7 Flash (Medium)	Google	-	-	1M	-	-	-	不可用	-	查看
Gemini 2.5 Flash-Lite (Reasoning)	Google	-	-	1M	US$0.1	-	358	不可用		查看
Gemini 2.0 Flash (experimental)	Google	-	-	1M	US$0.0	-	-	不可用		查看
Gemma 4 12B (Reasoning)	Google	-	12B	262k	US$0.1	-	85	🤗		查看

Google 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

Google 的所有发布

更多详情