GPT-6.1 Terra vs. GPT-6.1 Sol：发布比较

GPT-6.1 Terra 与 GPT-6.1 Sol 发布比较：分别包含 6 个和 5 个模型，各自具有不同的智能、性能与价格特征。下方对全部 11 个模型的关键指标进行了比较。

智能方面，GPT-6.1 Sol 得分最高：GPT-6.1 Sol (Max)（52），GPT-6.1 Terra 为 GPT-6.1 Terra (Max)（48）。
单任务成本方面，GPT-6.1 Terra 最低：GPT-6.1 Terra (Low)（$0.05），GPT-6.1 Sol 为 GPT-6.1 Sol (Low)（$0.13）。

比较的发布


	GPT-6.1 Sol (max)	GPT-6.1 Sol (xhigh)	GPT-6.1 Sol (high)	GPT-6.1 Terra (max)	GPT-6.1 Sol (medium)	GPT-6.1 Terra (xhigh)	GPT-6.1 Terra (high)	GPT-6.1 Sol (low)	GPT-6.1 Terra (medium)	GPT-6.1 Terra (low)	GPT-6.1 Terra (non-reasoning)
Intelligence Index	52	51	50	48	48	45	44	42	41	36	33
财务与会计	54	53	53	47	50	46	44	45	43	38	36
战略与运营	57	56	55	50	53	48	47	46	45	42	42
法律	58	57	56	49	54	48	47	50	46	42	35
医疗与健康	52	50	49	--	47	--	--	42	--	--	--
工程	54	53	52	49	50	46	45	44	42	35	32
经济学	59	58	58	54	56	52	51	52	49	44	38
AA-Briefcase v1.1	1555	1502	1465	1402	1359	1329	1264	1114	1192	1030	1229
GDPval-AA v2.1	1596	1539	1512	1468	1450	1403	1342	1316	1316	1199	1282
AutomationBench-AA	64.9%	66.6%	64.5%	60.2%	62.6%	59.9%	58.5%	52.6%	57.8%	56.2%	51.0%
Terminal-Bench 4.0	56.1%	54.0%	51.5%	55.6%	48.0%	46.5%	41.9%	30.8%	32.3%	15.2%	26.8%
SciCode	54.2%	55.7%	55.8%	55.1%	53.2%	53.4%	51.6%	53.2%	51.6%	52.4%	47.8%
Humanity's Last Exam	52.9%	52.6%	51.4%	46.2%	49.9%	43.7%	43.3%	47.4%	40.2%	35.8%	21.1%
GDP.pdf	31.0%	31.8%	32.0%	28.6%	30.0%	26.6%	28.0%	27.0%	28.4%	25.6%	23.2%
CritPt	31.7%	31.7%	30.0%	28.0%	27.7%	26.6%	25.7%	24.9%	21.4%	15.1%	4.9%
AA-Omniscience	42	41	41	30	40	29	28	38	27	24	4
AA-LCR v1.1	83.0%	79.7%	82.3%	82.7%	83.3%	81.7%	82.3%	84.0%	80.7%	81.0%	67.7%

每任务成本美元	$0.72	$0.39	$0.32	$0.40	$0.21	$0.19	$0.13	$0.13	$0.10	$0.05	$0.11
输入价格美元/100 万 Token	$2.00	$2.00	$2.00	$1.00	$2.00	$1.00	$1.00	$2.00	$1.00	$1.00	$1.00
输出价格美元/100 万 Token	$10.00	$10.00	$10.00	$5.00	$10.00	$5.00	$5.00	$10.00	$5.00	$5.00	$5.00
缓存命中价格美元/100 万 Token	$0.10	$0.10	$0.10	$0.05	$0.10	$0.05	$0.05	$0.10	$0.05	$0.05	$0.05
缓存写入价格美元/100 万 Token	$2.50	$2.50	$2.50	$1.25	$2.50	$1.25	$1.25	$2.50	$1.25	$1.25	$1.25

输出速度Token/秒	66	63	57	--	53	--	--	50	--	--	--
首 Token 延迟秒	325.58	162.56	73.81	--	4.38	--	--	2.71	--	--	--
首个回答 Token 时间秒	325.58	162.56	73.81	--	4.38	--	--	2.71	--	--	--
端到端响应时间秒	333.17	170.50	82.55	--	13.82	--	--	12.72	--	--	--
每任务耗时秒	571.46	278.87	230.67	--	152.29	--	--	79.09	--	--	--

上下文窗口	1M	1M	1M	1M	1M	1M	1M	1M	1M	1M	1M
开发商	OpenAI	OpenAI	OpenAI	OpenAI	OpenAI	OpenAI	OpenAI	OpenAI	OpenAI	OpenAI	OpenAI
许可证	专有	专有	专有	专有	专有	专有	专有	专有	专有	专有	专有
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：文本和图像
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	支持：文本	支持：文本	支持：文本	支持：文本
服务商

智能

Artificial Analysis Intelligence Index · Higher is better

速度

Output tokens per second · Higher is better

每任务成本

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

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

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 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 Terra

GPT-6.1 Sol

Pareto line

AA-Briefcase v1.1

GDPval-AA v2.1

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

速度与延迟

输出速度

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: GDPval-AA v2.1, AA-Briefcase v1.1, AA-Omniscience, 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

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 Terra vs. GPT-6.1 Sol：发布比较

智能

速度

每任务成本

智能

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

输出速度

Output Speed

Model Performance Representation

能力得分

能力指数

基准测试

AA-PersonalityBenchNew

性格指数