Scaleway:模型智能、性能与价格

Scaleway
Scaleway

本分析旨在帮助你根据使用场景,选择 Scaleway 提供的最佳模型。

最智能

Updated
#1
GLM-5.2 (max)GLM-5.2 (max)
34
#2
GLM-5.2 (Non-reasoning)GLM-5.2 (Non-reasoning)
22
#3
Qwen3.6 35B A3BQwen3.6 35B A3B
19
#4
Qwen3.6 35B A3B (Non-reasoning)Qwen3.6 35B A3B (Non-reasoning)
15
#5
Gemma 4 26B A4B (Non-reasoning)Gemma 4 26B A4B (Non-reasoning)
13

Intelligence Index

共 9 个模型

速度最快

#1
Gemma 4 26B A4B (Non-reasoning)Gemma 4 26B A4B (Non-reasoning)
171 t/s
#2
Qwen3 Coder 30B A3BQwen3 Coder 30B A3B
143 t/s
#3
Qwen3.6 35B A3B (Non-reasoning)Qwen3.6 35B A3B (Non-reasoning)
140 t/s
#4
Qwen3.6 35B A3BQwen3.6 35B A3B
128 t/s
#5
gpt-oss-120b (high)gpt-oss-120b (high)
118 t/s

输出速度

共 9 个模型

价格最低

#1
gpt-oss-120b (high)gpt-oss-120b (high)
$0.22
#2
Gemma 4 26B A4B (Non-reasoning)Gemma 4 26B A4B (Non-reasoning)
$0.28
#3
Qwen3 Coder 30B A3BQwen3 Coder 30B A3B
$0.30
#4
Qwen3.6 35B A3BQwen3.6 35B A3B
$0.44
#5
Qwen3.6 35B A3B (Non-reasoning)Qwen3.6 35B A3B (Non-reasoning)
$0.44

每 100 万 token 的混合价格

共 9 个模型

Scaleway 提供 9 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,Scaleway 上表现最好的模型是 GLM-5.2 (max)(34)、GLM-5.2 (Non-reasoning)(22)和Qwen3.6 35B A3B(19)。
  • 输出速度方面,最快的模型是 Gemma 4 26B A4B (Non-reasoning)(171 t/s)、Qwen3 Coder 30B A3B(143 t/s)和Qwen3.6 35B A3B (Non-reasoning)(140 t/s)。
  • 延迟方面,Gemma 4 26B A4B (Non-reasoning)(0.91 秒)、Qwen3.6 35B A3B (Non-reasoning)(1.00 秒)和Qwen3 Coder 30B A3B(1.08 秒) 的首个答案 Token 延迟最低。
  • 价格方面,gpt-oss-120b (high)($0.22)、Gemma 4 26B A4B (Non-reasoning)($0.28)和Qwen3 Coder 30B A3B($0.30) 每 100 万 token 的混合价格最低。
  • 上下文窗口方面,GLM-5.2 (max)(262k)、GLM-5.2 (Non-reasoning)(262k)和Qwen3.6 35B A3B(262k) 支持 Scaleway 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

No data available

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
Z AI 标志
GLM-5.2 (max)
262k
开放
34
$4.37
94
1.64
28.25
21.29
Z AI 标志
GLM-5.2 (Non-reasoning)
262k
开放
22*
--
92
1.69
7.14
--
Alibaba 标志
Qwen3.6 35B A3B
262k
开放
19
$0.37
128
0.99
47.10
42.20
Alibaba 标志
Qwen3.6 35B A3B (Non-reasoning)
262k
开放
15*
--
140
1.00
4.56
--
Google 标志
Gemma 4 26B A4B (Non-reasoning)
262k
开放
13*
--
171
0.91
3.84
--
OpenAI 标志
gpt-oss-120b (high)
128k
开放
12
$0.12
118
1.32
22.53
16.97
Alibaba 标志
Qwen3 235B 2507 (Non-reasoning)
250k
开放
12*
--
91
1.44
6.91
--
Alibaba 标志
Qwen3 Coder 30B A3B
128k
开放
10*
--
143
1.08
4.58
--
Meta 标志
Llama 3.3 70B
100k
开放
8*
--
81
1.35
7.55
--

关键定义

常见问题

关于 Scaleway 的常见问题