Modular:模型智能、性能与价格

Modular
Modular

本分析旨在帮助你根据使用场景,选择 Modular 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
MiniMax-M3MiniMax-M3
29
#4
Kimi K2.7 CodeKimi K2.7 Code
26
#5
GLM-5.2 (Non-reasoning)GLM-5.2 (Non-reasoning)
22

Intelligence Index

共 7 个模型

速度最快

#1
Gemma 4 31B (Non-reasoning) (NVFP4)Gemma 4 31B (Non-reasoning) (NVFP4)
232 t/s
#2
GLM-5.2 (max)GLM-5.2 (max)
217 t/s
#3
MiniMax-M3MiniMax-M3
214 t/s
#4
GLM-5.3 (max)GLM-5.3 (max)
196 t/s
#5
Kimi K2.7 CodeKimi K2.7 Code
192 t/s

输出速度

共 7 个模型

价格最低

#1
MiniMax-M3MiniMax-M3
$0.22
#2
Gemma 4 31B (NVFP4)Gemma 4 31B (NVFP4)
$0.29
#3
Gemma 4 31B (Non-reasoning) (NVFP4)Gemma 4 31B (Non-reasoning) (NVFP4)
$0.29
#4
GLM-5.3 (max)GLM-5.3 (max)
$0.90
#5
GLM-5.2 (max)GLM-5.2 (max)
$0.90

每 100 万 token 的混合价格

共 7 个模型

Modular 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,Modular 上表现最好的模型是 GLM-5.3 (max)(45)、GLM-5.2 (max)(34)和MiniMax-M3(29)。
  • 输出速度方面,最快的模型是 Gemma 4 31B (Non-reasoning) (NVFP4)(232 t/s)、GLM-5.2 (max)(217 t/s)和MiniMax-M3(214 t/s)。
  • 延迟方面,Gemma 4 31B (Non-reasoning) (NVFP4)(0.51 秒)、GLM-5.2 (Non-reasoning)(0.69 秒)和GLM-5.2 (max)(9.91 秒) 的首个答案 Token 延迟最低。
  • 价格方面,MiniMax-M3($0.22)、Gemma 4 31B (NVFP4)($0.29)和Gemma 4 31B (Non-reasoning) (NVFP4)($0.29) 每 100 万 token 的混合价格最低。 各模型价格最多相差 4.1 倍。
  • 上下文窗口方面,MiniMax-M3(1M)、Kimi K2.7 Code(262k)和Gemma 4 31B (NVFP4)(262k) 支持 Modular 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 v4.3.2 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)

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

Agentic tool use

Kubernetes incident root-cause analysis

Visual reasoning

Medical long context 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
Z AI 标志
GLM-5.3 (max)
164k
开放
45
$2.05
196
0.64
13.42
10.22
Z AI 标志
GLM-5.2 (max)
164k
开放
34
$0.88
217
0.67
12.22
9.24
MiniMax 标志
MiniMax-M3
1M
开放
29
$0.46
214
0.92
12.61
9.35
Kimi 标志
Kimi K2.7 Code
262k
开放
26
$1.69
192
0.58
14.78
11.60
Z AI 标志
GLM-5.2 (Non-reasoning)
164k
开放
22*
--
184
0.69
3.40
--
Google 标志
Gemma 4 31B (NVFP4)
262k
开放
19*
--
146
0.51
15.82
11.88
Google 标志
Gemma 4 31B (Non-reasoning) (NVFP4)
262k
开放
14*
--
232
0.51
2.66
--

关键定义

常见问题

关于 Modular 的常见问题