GPT-6.1 Sol vs. Claude Sonnet 5.5：发布比较

GPT-6.1 Sol 与 Claude Sonnet 5.5 发布比较：分别包含 5 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 10 个模型的关键指标进行了比较。

智能方面，Claude Sonnet 5.5 得分最高：Claude Sonnet 5.5 (Max, Default Fallback)（56），GPT-6.1 Sol 为 GPT-6.1 Sol (Max)（52）。
输出速度方面，Claude Sonnet 5.5 最快：Claude Sonnet 5.5 (Max, Default Fallback)（134 token/秒），GPT-6.1 Sol 为 GPT-6.1 Sol (Max)（55 token/秒）。
单任务成本方面，GPT-6.1 Sol 最低：GPT-6.1 Sol (Low)（$0.13），Claude Sonnet 5.5 为 Claude Sonnet 5.5 (Low, Default Fallback)（$0.35）。

比较的发布


	Claude Sonnet 5.5 (max with fallback)	Claude Sonnet 5.5 (xhigh with fallback)	GPT-6.1 Sol (max)	GPT-6.1 Sol (xhigh)	GPT-6.1 Sol (high)	GPT-6.1 Sol (medium)	Claude Sonnet 5.5 (high with fallback)	GPT-6.1 Sol (low)	Claude Sonnet 5.5 (medium with fallback)	Claude Sonnet 5.5 (low with fallback)
Intelligence Index	56	52	52	51	50	48	47	42	41	36
财务与会计	57	52	54	53	53	50	47	45	41	38
战略与运营	60	56	57	56	55	53	52	46	45	41
法律	56	52	58	57	56	54	49	50	44	41
医疗与健康	58	--	51	--	--	--	--	--	--	--
工程	58	54	54	53	52	50	48	44	42	38
经济学	61	56	59	58	58	56	52	52	47	44
AA-Briefcase v1.1	1817	1751	1557	1504	1465	1361	1636	1117	1441	1272
GDPval-AA v2.1	1838	1728	1594	1538	1511	1450	1549	1315	1323	1175
AutomationBench-AA	71.8%	65.5%	64.9%	66.6%	64.5%	62.6%	59.4%	52.6%	54.9%	49.4%
Terminal-Bench 4.0	63.6%	57.1%	56.1%	54.0%	51.5%	48.0%	43.9%	30.8%	29.8%	20.7%
SciCode	61.0%	57.3%	54.2%	55.7%	55.8%	53.2%	53.7%	53.2%	52.9%	49.1%
Humanity's Last Exam	55.0%	50.0%	52.9%	52.6%	51.4%	49.9%	45.8%	47.4%	39.8%	36.2%
GDP.pdf	25.8%	24.6%	31.0%	31.8%	32.0%	30.0%	25.2%	27.0%	20.2%	16.0%
CritPt	31.4%	31.1%	31.7%	31.7%	30.0%	27.7%	24.6%	24.9%	16.9%	11.4%
AA-Omniscience	32	24	42	41	41	40	21	38	20	19
AA-LCR v1.1	82.7%	79.7%	83.0%	79.7%	82.3%	83.3%	78.0%	84.0%	76.3%	76.0%

每任务成本美元	$5.46	$2.01	$0.72	$0.39	$0.32	$0.21	$0.88	$0.13	$0.48	$0.35
输入价格美元/100 万 Token	$2.00	$2.00	$2.00	$2.00	$2.00	$2.00	$2.00	$2.00	$2.00	$2.00
输出价格美元/100 万 Token	$10.00	$10.00	$10.00	$10.00	$10.00	$10.00	$10.00	$10.00	$10.00	$10.00
缓存命中价格美元/100 万 Token	$0.10	$0.10	$0.10	$0.10	$0.10	$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	$2.50	$2.50	$2.50	$2.50	$2.50

输出速度Token/秒	134	110	55	52	48	44	105	43	106	107
首 Token 延迟秒	388.54	31.59	239.97	133.08	40.09	4.12	10.46	2.80	1.29	1.11
首个回答 Token 时间秒	388.54	31.59	239.97	133.08	40.09	4.12	10.46	2.80	1.29	1.11
端到端响应时间秒	392.26	36.15	249.02	142.75	50.55	15.54	15.22	14.42	6.00	5.78
每任务耗时秒	908.68	424.16	687.68	337.39	266.05	183.98	216.82	91.58	122.29	82.40

上下文窗口	1M	1M	1M	1M	1M	1M	1M	1M	1M	1M
开发商	Anthropic	Anthropic	OpenAI	OpenAI	OpenAI	OpenAI	Anthropic	OpenAI	Anthropic	Anthropic
许可证	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
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
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 Sol

Claude Sonnet 5.5

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

AA-PersonalityBenchNew

Model AvsModel B

AA-PersonalityBench: Expressiveness Index, GPT-6.1 Sol (max) vs Claude Sonnet 5.5 (max with fallback)

Chance each model’s answer is judged to show more of each trait from their Elo gap · 50% is an even match

GPT-6.1 Sol (max)

Claude Sonnet 5.5 (max with fallback)

Lexically Varied

91%

Metaphorical

12%

88%

Natural Sounding

62%

38%

Eloquent

40%

60%

Literate

52%

48%

GPT-6.1 Sol vs. Claude Sonnet 5.5：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

AA-PersonalityBenchNew

AA-PersonalityBench: Expressiveness Index, GPT-6.1 Sol (max) vs Claude Sonnet 5.5 (max with fallback)