Multiverse Computing:模型智能、性能与价格

Multiverse Computing
Multiverse Computing

本分析旨在帮助你根据使用场景,选择 Multiverse Computing 提供的最佳模型。

最智能

Updated
#1
GLM-5.3 (max)GLM-5.3 (max)
45
#2
GLM-5.2 (max)GLM-5.2 (max)
34
#3
Qwen3.8 27B (xhigh)Qwen3.8 27B (xhigh)
34
#4
Qwen3.8 27B (medium)Qwen3.8 27B (medium)
28
#5
Quasar 438B (max)Quasar 438B (max)
27

Intelligence Index

共 7 个模型

速度最快

#1
Qwen3.8 27B (non-reasoning)Qwen3.8 27B (non-reasoning)
214 t/s
#2
Qwen3.8 27B (xhigh)Qwen3.8 27B (xhigh)
195 t/s
#3
Qwen3.8 27B (medium)Qwen3.8 27B (medium)
193 t/s
#4
Qwen3.8 27B (low)Qwen3.8 27B (low)
187 t/s
#5
GLM-5.3 (max)GLM-5.3 (max)
138 t/s

输出速度

共 7 个模型

价格最低

#1
Qwen3.8 27B (xhigh)Qwen3.8 27B (xhigh)
$0.56
#2
Qwen3.8 27B (medium)Qwen3.8 27B (medium)
$0.56
#3
Qwen3.8 27B (low)Qwen3.8 27B (low)
$0.56
#4
Qwen3.8 27B (non-reasoning)Qwen3.8 27B (non-reasoning)
$0.56
#5
Quasar 438B (max)Quasar 438B (max)
$0.72

每 100 万 token 的混合价格

共 7 个模型

Multiverse Computing 提供 7 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,Multiverse Computing 上表现最好的模型是 GLM-5.3 (max)(45)、GLM-5.2 (max)(34)和Qwen3.8 27B (xhigh)(34)。
  • 输出速度方面,最快的模型是 Qwen3.8 27B (non-reasoning)(214 t/s)、Qwen3.8 27B (xhigh)(195 t/s)和Qwen3.8 27B (medium)(193 t/s)。 各模型之间的速度差异显著,最快与最慢相差 55%。
  • 延迟方面,Qwen3.8 27B (non-reasoning)(0.80 秒)、Qwen3.8 27B (xhigh)(11.05 秒)和Qwen3.8 27B (medium)(11.19 秒) 的首个答案 Token 延迟最低。
  • 价格方面,Qwen3.8 27B (xhigh)($0.56)、Qwen3.8 27B (medium)($0.56)和Qwen3.8 27B (low)($0.56) 每 100 万 token 的混合价格最低。
  • 上下文窗口方面,GLM-5.3 (max)(1M)、GLM-5.2 (max)(1M)和Quasar 438B (max)(1M) 支持 Multiverse Computing 上最大的上下文窗口。
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 v4.3.2 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

Intelligence Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better
查看更多

Agentic knowledge work, (Elo-500)/2000

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

Agentic SaaS workflows

Agentic coding & terminal use

SciCodeUnder review

Coding

Reasoning & knowledge

Professional document reasoning, All-pass

CritPtUnder review

Physics reasoning

Long context reasoning

Legal agentic work, criterion pass rate

Agentic business operations

Agentic scientific research workflows in a terminal

Quantitative analysis on spreadsheets & documents

No data available

Kubernetes incident root-cause analysis

Visual reasoning

Medical long context reasoning

Intelligence Index 与价格

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

上下文窗口

上下文窗口

Context window: tokens limit · Higher is better

价格

Intelligence Index 与价格

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

性能摘要

输出速度与价格

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

速度

按输出速度(每秒 token 数)衡量

输出速度

Output tokens per second · Higher is better

延迟

按首 Token 延迟(秒)衡量

延迟: 首个答案 Token 延迟

收到首个回答 token 的秒数 · 包含推理模型的“思考”时间

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

端到端响应时间与价格

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

进一步分析
Z AI 标志
GLM-5.3 (max)
1M
开放
45
$6.82
123
1.33
21.70
16.30
Z AI 标志
GLM-5.2 (max)
1M
开放
34
$2.31
107
1.20
24.65
18.75
Alibaba 标志
Qwen3.8 27B (xhigh)
262k
开放
34
$1.98
197
0.66
13.35
10.15
Alibaba 标志
Qwen3.8 27B (medium)
262k
开放
28
$2.36
186
0.79
14.21
10.74
Multiverse Computing 标志
Quasar 438B (max)
1M
专有
27
$2.02
143
1.15
18.65
14.00
Alibaba 标志
Qwen3.8 27B (low)
262k
开放
26
$2.19
192
0.65
13.68
10.42
Alibaba 标志
Qwen3.8 27B (non-reasoning)
262k
开放
20
$5.69
209
0.77
3.17
--
Mistral 标志
Mistral Small 3.1
128k
开放
7
$0.04
75
1.11
7.73
--

关键定义

常见问题

关于 Multiverse Computing 的常见问题