GPT-6 Luna vs. JT-4.1 Flash 236B A21B：发布比较

GPT-6 Luna 与 JT-4.1 Flash 236B A21B 发布比较：分别包含 6 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 8 个模型的关键指标进行了比较。

智能方面，GPT-6 Luna 得分最高：GPT-6 Luna (Max)（38），JT-4.1 Flash 236B A21B 为 JT-4.1 Flash 236B A21B (Reasoning)（34）。

比较的发布


	GPT-6 Luna (max)	GPT-6 Luna (xhigh)	JT-4.1 Flash 236B A21B	GPT-6 Luna (high)	GPT-6 Luna (medium)	JT-4.1 Flash 236B A21B (non-reasoning)	GPT-6 Luna (low)	GPT-6 Luna (non-reasoning)
Intelligence Index	38	35	34	33	30	27*	22	18
财务与会计	40	37	40	36	33	--	24	20
战略与运营	46	43	41	41	37	--	23	20
法律	40	37	44	35	33	--	25	19
医疗与健康	37	--	--	--	--	--	--	--
工程	37	34	36	32	29	--	23	21
经济学	45	42	47	40	37	--	30	24
AA-Briefcase v1.1	1335	1237	1089	1186	1099	--	741	903
GDPval-AA v2.1	1432	1364	1324	1340	1262	1123	1033	1045
AutomationBench-AA	53.2%	47.8%	46.5%	47.8%	40.5%	--	12.0%	9.1%
Terminal-Bench 4.0	12.6%	8.1%	3.0%	4.5%	2.5%	--	0.0%	1.5%
SciCode	54.6%	51.7%	52.0%	50.3%	50.9%	--	46.9%	43.1%
Humanity's Last Exam	38.5%	34.3%	43.6%	32.9%	28.3%	17.8%	20.3%	8.6%
GDP.pdf	22.8%	18.6%	8.6%	18.2%	13.8%	--	9.0%	5.8%
CritPt	19.4%	17.4%	14.0%	15.4%	10.6%	0.0%	2.6%	1.1%
AA-Omniscience	1	−2	21	−6	−5	−9	−9	−22
AA-LCR v1.1	83.3%	80.0%	78.3%	79.3%	78.3%	71.3%	74.0%	39.7%

每任务成本美元	$0.07	$0.04	--	$0.03	$0.02	--	$0.0045	$0.01
输入价格美元/100 万 Token	$0.10	$0.10	--	$0.10	$0.10	--	$0.10	$0.10
输出价格美元/100 万 Token	$0.50	$0.50	--	$0.50	$0.50	--	$0.50	$0.50
缓存命中价格美元/100 万 Token	$0.01	$0.01	--	$0.01	$0.01	--	$0.01	$0.01
缓存写入价格美元/100 万 Token	$0.125	$0.125	--	$0.125	$0.125	--	$0.125	$0.125

输出速度Token/秒	124	126	--	118	--	--	125	128
首 Token 延迟秒	92.88	25.56	--	12.79	--	--	1.78	0.81
首个回答 Token 时间秒	92.88	25.56	--	12.79	--	--	1.78	0.81
端到端响应时间秒	96.91	29.52	--	17.03	--	--	5.77	4.72
每任务耗时秒	404.08	217.75	--	165.18	--	--	16.54	29.32

上下文窗口	1M	1M	262k	1M	1M	262k	1M	1M
开发商	OpenAI	OpenAI	China Mobile	OpenAI	OpenAI	China Mobile	OpenAI	OpenAI
许可证	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
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
服务商			--			--

* 估计值

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

Estimate (independent evaluation forthcoming)

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 Luna

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 results are not available for JT-4.1 Flash 236B A21B

GPT-6 Luna vs. JT-4.1 Flash 236B A21B：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