SpaceXAI:模型智能、性能与价格

SpaceXAI
SpaceXAI

本分析旨在帮助你根据使用场景,选择 SpaceXAI 提供的最佳模型。

最智能

Updated
#1
Grok 4.6 (high)Grok 4.6 (high)
44
#2
Grok 4.6 (xhigh)Grok 4.6 (xhigh)
44
#3
Grok 4.6 (medium)Grok 4.6 (medium)
43
#4
Grok 4.5 (high)Grok 4.5 (high)
39
#5
Grok 4.6 (low)Grok 4.6 (low)
35

Intelligence Index

共 15 个模型

速度最快

#1
Grok 4.3 (high)Grok 4.3 (high)
119 t/s
#2
Grok 4.3 (Non-reasoning)Grok 4.3 (Non-reasoning)
115 t/s
#3
Grok 4.3 (medium)Grok 4.3 (medium)
114 t/s
#4
Grok 4.3 (low)Grok 4.3 (low)
112 t/s
#5
Grok 3 FastGrok 3 Fast
110 t/s

输出速度

共 15 个模型

价格最低

#1
Grok 3 mini Reasoning (high)Grok 3 mini Reasoning (high)
$0.16
#2
Grok Build 0.1 0616Grok Build 0.1 0616
$0.54
#3
Grok 3 mini Reasoning (high) FastGrok 3 mini Reasoning (high) Fast
$0.57
#4
Grok 4.20 0309 v2Grok 4.20 0309 v2
$0.64
#5
Grok 4.3 (high)Grok 4.3 (high)
$0.64

每 100 万 token 的混合价格

共 15 个模型

SpaceXAI 提供 15 个模型,每个模型的智能、性能和价格特征各不相同。 下方对比了各模型的关键指标。

  • 智能方面,SpaceXAI 上表现最好的模型是 Grok 4.6 (high)(44)、Grok 4.6 (xhigh)(44)和Grok 4.6 (medium)(43)。
  • 输出速度方面,最快的模型是 Grok 4.3 (high)(119 t/s)、Grok 4.3 (Non-reasoning)(115 t/s)和Grok 4.3 (medium)(114 t/s)。
  • 延迟方面,Grok 4.20 0309 v2 (Non-reasoning)(0.64 秒)、Grok 3 Fast(0.71 秒)和Grok 4.3 (Non-reasoning)(0.74 秒) 的首个答案 Token 延迟最低。
  • 价格方面,Grok 3 mini Reasoning (high)($0.16)、Grok Build 0.1 0616($0.54)和Grok 3 mini Reasoning (high) Fast($0.57) 每 100 万 token 的混合价格最低。 各模型价格最多相差 3.9 倍。
  • 上下文窗口方面,Grok 4.20 0309 v2(2M)、Grok 4.20 0309 v2 (Non-reasoning)(2M)和Grok 4.3 (high)(1M) 支持 SpaceXAI 上最大的上下文窗口。

亮点

Updated
Artificial Analysis Intelligence Index · Higher is better
Output tokens per second · Higher is better
USD per 1M tokens (blended) · Lower is better

智能评测

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.3 incorporates 10 evaluations: AA-Briefcase, GDPval-AA v2, AutomationBench-AA, Terminal-Bench v4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1
Estimate (independent evaluation forthcoming)

Intelligence Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better
See more

Agentic knowledge work, (Elo-500)/2000

Agentic real-world work tasks, (Elo-500)/2000

Agentic SaaS workflows

Agentic coding & terminal use

Coding

Reasoning & knowledge

Professional document reasoning, All-pass

Physics reasoning

Long context reasoning

Legal agentic work, criterion pass rate

Agentic business operations

Quantitative analysis on spreadsheets & documents

Instruction following

Agentic tool use

Long-horizon agentic tasks

Kubernetes incident root-cause analysis

Visual reasoning

Intelligence Index vs. Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended)
Most attractive quadrant
Pareto line

上下文窗口

Context Window

Context window: tokens limit · Higher is better

价格

Intelligence Index vs. Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended)
Most attractive quadrant
Pareto line

性能摘要

Output Speed vs. Price

Output speed: output tokens per second · USD per 1M tokens (blended)
Most attractive quadrant
Pareto line

速度

按输出速度(每秒 token 数)衡量

Output Speed

Output tokens per second · Higher is better

延迟

按首 Token 延迟(秒)衡量

Latency: Time To First Answer Token

Seconds to first answer token received · Accounts for reasoning model 'thinking' time

端到端响应时间

Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed

End-to-End Response Time vs. Price

End-to-end response time: end-to-end seconds to output 500 tokens · USD per 1M tokens (blended)
Most attractive quadrant
Pareto line

进一步分析
SpaceXAI 标志
Grok 4.6 (high)
500k
专有
44
$1.86
59
40.86
49.41
--
SpaceXAI 标志
Grok 4.6 (xhigh)
500k
专有
44
$2.32
55
41.74
50.84
--
SpaceXAI 标志
Grok 4.6 (medium)
500k
专有
43
$1.50
55
36.05
45.14
--
SpaceXAI 标志
Grok 4.5 (high)
500k
专有
39
$1.04
61
7.45
15.65
--
SpaceXAI 标志
Grok 4.6 (low)
500k
专有
35
$0.48
53
6.30
15.65
--
SpaceXAI 标志
Grok Build 0.1 0616
256k
专有
27*
--
59
0.60
42.76
33.73
SpaceXAI 标志
Grok 4.20 0309 v2
2M
专有
26*
--
101
21.12
26.06
--
SpaceXAI 标志
Grok 4.3 (high)
1M
专有
25
$0.17
119
18.32
22.51
--
SpaceXAI 标志
Grok 4.20 0309
2M
专有
25*
--
--
--
--
--
SpaceXAI 标志
Grok 4.3 (medium)
1M
专有
25*
--
114
11.36
15.73
--
SpaceXAI 标志
Grok 4.3 (low)
1M
专有
24*
--
112
5.63
10.10
--
SpaceXAI 标志
Grok 3 mini Reasoning (high)
131k
专有
15*
--
64
0.73
39.54
31.05
SpaceXAI 标志
Grok 3 mini Reasoning (high) Fast
131k
专有
15*
--
76
0.72
33.83
26.49
SpaceXAI 标志
Grok 4.20 0309 (Non-reasoning)
2M
专有
15*
--
--
--
--
--
SpaceXAI 标志
Grok 4.3 (Non-reasoning)
1M
专有
15
$0.14
115
0.74
5.07
--
SpaceXAI 标志
Grok 4.20 0309 v2 (Non-reasoning)
2M
专有
14*
--
90
0.64
6.21
--
SpaceXAI 标志
Grok 3 Fast
131k
专有
12*
--
110
0.71
5.28
--

关键定义

常见问题

关于 SpaceXAI 的常见问题