GPT-6.1 Sol vs. Gemma 4 12B：发布比较

GPT-6.1 Sol 与 Gemma 4 12B 发布比较：分别包含 5 个和 2 个模型，各自具有不同的智能、性能与价格特征。下方对全部 7 个模型的关键指标进行了比较。

比较的发布


	GPT-6.1 Sol (max)	GPT-6.1 Sol (xhigh)	GPT-6.1 Sol (high)	GPT-6.1 Sol (medium)	GPT-6.1 Sol (low)	Gemma 4 12B	Gemma 4 12B (non-reasoning)
Intelligence Index	55	52	50	46	35	--	--
财务与会计	56	55	53	51	44	--	--
战略与运营	58	57	55	53	46	--	--
法律	54	54	52	49	43	--	--
医疗与健康	52	51	49	46	40	--	--
工程	59	57	55	52	43	--	--
经济学	56	55	53	50	43	--	--
AA-Briefcase v1.1	1555	1503	1469	1360	1114	--	--
AutomationBench-AA	64.9%	66.6%	64.5%	62.6%	52.6%	0.7%	--
Terminal-Bench 4.0	56.1%	54.0%	51.5%	48.0%	30.8%	--	--
FrontierCode 2.0	40.6%	38.5%	36.7%	33.4%	20.2%	--	--
AA-Omniscience v1.1	42	42	41	40	38	--	--
GDP.pdf	31.0%	31.8%	32.0%	30.0%	27.0%	--	--
HLE-Diamond	58.8%	55.8%	51.9%	46.0%	38.2%	--	--
CritPt v2 (Hard Subset)	69.5%	69.5%	68.5%	67.0%	62.5%	--	--
Terminal-Bench-Science 0.1	58.1%	50.5%	46.2%	37.1%	11.0%	--	--

每任务成本美元	$1.27	$0.76	$0.59	$0.36	$0.16	--	--
输入价格美元/100 万 Token	$2.00	$2.00	$2.00	$2.00	$2.00	$0.10	$0.10
输出价格美元/100 万 Token	$10.00	$10.00	$10.00	$10.00	$10.00	$0.30	$0.30
缓存命中价格美元/100 万 Token	$0.10	$0.10	$0.10	$0.10	$0.10	--	--
缓存写入价格美元/100 万 Token	$2.50	$2.50	$2.50	$2.50	$2.50	--	--

每任务耗时分钟	19.9	9.2	6.5	3.8	1.8	--	--
输出速度tok/s	57	55	58	60	55	84	68
首个答案 Token 延迟秒	176.93	70.31	36.93	4.36	2.46	26.77	3.89
首 Token 延迟秒	176.93	70.31	36.93	4.36	2.46	3.53	3.89
端到端时间单次请求工作负载的平均值（秒）	413.89	206.95	142.10	68.57	61.16	64.05	28.15

上下文窗口	1M	1M	1M	1M	1M	262k	262k
开发商	OpenAI	OpenAI	OpenAI	OpenAI	OpenAI	Google	Google
许可证	专有	专有	专有	专有	专有	开放	开放
输入模态	支持：文本和图像	支持：文本和图像	支持：文本和图像	支持：文本和图像	支持：文本和图像	支持：文本、图像、语音和视频	支持：文本、图像、语音和视频
输出模态	支持：文本	支持：文本	支持：文本	支持：文本	支持：文本	支持：文本	支持：文本
服务商

Updated

智能

Artificial Analysis Intelligence Index · Higher is better

每任务耗时

Inference time (minutes) per Intelligence Index task · Lower is better

每任务成本

Weighted average cost (USD) per Intelligence Index task · Lower is better

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

GPT-6.1 Sol

Pareto line

AA-Briefcase v1.1

AutomationBench-AA

单任务成本（美元，对数刻度）

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

基准测试

AA-PersonalityBenchNew

性格指数

每个轴对应 8 个性格指数之一：其特质 Elo z 分数的平均值，在基准测试中所有已评估模型之间换算为 1 到 100 的百分位排名

GPT-6.1 Sol vs. Gemma 4 12B：发布比较

智能

每任务耗时

每任务成本

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

基准测试

AA-PersonalityBenchNew

性格指数