Skip to content
LMC Feed-Models, Papers, Benchmarks. Zero Fluff.Live

Alibaba

53 个模型 · 平均评分 56

Last updated: 7m ago
模型53
平均评分56
最佳排名#88
顶级模型Qwen3.5 397B A17B

服务商优势

平均综合评分
56
最佳模型
Qwen3.5 397B A17B
Score 79
价格范围 (每百万输出)
Free - $6.16
1 个免费模型
平均上下文窗口
459K
模型总数
53
功能覆盖
5/7
项功能

模型时间线

Sep 2026Qwen3.8 Omni FlashScore 40
Sep 2026Qwen3.8 Max (0902)Score 76
Aug 2026Qwen3.8 FlashScore 40
Aug 2026Qwen3.8 27BScore 73
Aug 2026Qwen3.8 27B (free)Score 73
Aug 2026Qwen3.8 2.4T A95BScore 40
Jul 2026Qwen3.7 FlashScore 40
Jun 2026Qwen3.7 PlusScore 76
May 2026Qwen3.7 MaxScore 75
Apr 2026Qwen3.5 Plus 2026-04-20Score 75
Apr 2026Qwen3.6 FlashScore 40
Apr 2026Qwen3.6 35B A3BScore 40
Apr 2026Qwen3.6 Max PreviewScore 75
Apr 2026Qwen3.6 27BScore 40
Apr 2026Qwen3.6 PlusScore 74
Mar 2026Qwen3.5-9BScore 67
Feb 2026Qwen3.5-35B-A3BScore 76
Feb 2026Qwen3.5-27BScore 77
Feb 2026Qwen3.5-122B-A10BScore 78
Feb 2026Qwen3.5-FlashScore 69
Feb 2026Qwen3.5 Plus 2026-02-15Score 68
Feb 2026Qwen3.5 397B A17BScore 79
Feb 2026Qwen3 Max ThinkingScore 68
Feb 2026Qwen3 Coder NextScore 40
Oct 2025Qwen3 VL 32B InstructScore 40
Oct 2025Qwen3 VL 8B ThinkingScore 40
Oct 2025Qwen3 VL 8B InstructScore 40
Oct 2025Qwen3 VL 30B A3B ThinkingScore 40
Oct 2025Qwen3 VL 30B A3B InstructScore 40
Sep 2025Qwen3 VL 235B A22B ThinkingScore 69
Sep 2025Qwen3 VL 235B A22B InstructScore 69
Sep 2025Qwen3 MaxScore 67
Sep 2025Qwen3 Coder PlusScore 40
Sep 2025Qwen3 Coder FlashScore 40
Sep 2025Qwen3 Next 80B A3B ThinkingScore 67
Sep 2025Qwen3 Next 80B A3B InstructScore 67
Sep 2025Qwen Plus 0728Score 40
Aug 2025Qwen3 30B A3B Thinking 2507Score 64
Jul 2025Qwen3 Coder 30B A3B InstructScore 40
Jul 2025Qwen3 30B A3B Instruct 2507Score 64
Jul 2025Qwen3 235B A22B Thinking 2507Score 65
Jul 2025Qwen3 Coder 480B A35BScore 40
Jul 2025Qwen3 235B A22B Instruct 2507Score 65
Apr 2025Qwen3 30B A3BScore 64
Apr 2025Qwen3 8BScore 61
Apr 2025Qwen3 14BScore 40
Apr 2025Qwen3 32BScore 40
Apr 2025Qwen3 235B A22BScore 54
Feb 2025Qwen2.5 VL 72B InstructScore 40
Feb 2025Qwen-PlusScore 40
Nov 2024Qwen2.5 Coder 32B InstructScore 40
Oct 2024Qwen2.5 7B InstructScore 38
Sep 2024Qwen2.5 72B InstructScore 40

价格分布

Free
1个模型
Budget
36个模型
Standard
16个模型
Premium
0个模型

功能覆盖

Vision
27/53
Function Calling
51/53
Reasoning
34/53
JSON Mode
53/53
Streaming
53/53
Web Search
0/53
Image Output
0/53

最近添加 (3)

最近30天
Qwen3.8 Omni Flash
Sep 2026
40
Qwen3.8 Max (0902)
Sep 2026
76
Qwen3.8 Flash
Aug 2026
40

基准测试领先

Arena Elo
Qwen3.6 Max Preview
1460 elo
MMLU-Pro
Qwen3.5 397B A17B
87.8%
IFEval
Qwen2.5 7B Instruct
75.85%

Verification & Source Coverage

把模型目录、服务状态和官方链接放在一起查看，能更快判断这个服务商页面是否可靠且最新。

目录校验时间
Sep 23, 2026

来自实时模型目录缓存。

状态校验时间
Sep 23, 2026

来自服务状态抓取。

最新发布
Sep 21, 2026

最早追踪到 Sep 19, 2024

来源覆盖
53 实时

无嵌入产品模型

APIDocs

Operational Health

在定价和模型深度的同时追踪可靠性，使服务商选择建立在运营现实之上。

Full status page
当前状态
not monitored

Status monitoring via official APIs not yet available

30天正常运行
-

Rolling availability across the last 30 days.

稳定性评分
-

Composite reliability indicator from recent status behavior.

30天内事件
0

Includes degraded performance, partial outages, and major incidents.

Provider Catalog

Sort:
#ModelScore
88Qwen3.5 397B A17B
79
110Qwen3.5-122B-A10B
78
112Qwen3.5-27B
77
119Qwen3.5-35B-A3B
76
122Qwen3.8 Max (0902)
76
123Qwen3.7 Plus
76
129Qwen3.7 Max
75
130Qwen3.5 Plus 2026-04-20
75
131Qwen3.6 Max Preview
75
136Qwen3.6 Plus
74
141Qwen3.8 27B
73
145Qwen3.8 27B (free)
73
169Qwen3 VL 235B A22B Thinking
69
170Qwen3 VL 235B A22B Instruct
69
175Qwen3.5-Flash
69
177Qwen3.5 Plus 2026-02-15
68
178Qwen3 Max Thinking
68
182Qwen3 Max
67
185Qwen3 Next 80B A3B Thinking
67
186Qwen3 Next 80B A3B Instruct
67
188Qwen3.5-9B
67
195Qwen3 235B A22B Thinking 2507
65
198Qwen3 235B A22B Instruct 2507
65
199Qwen3 30B A3B Thinking 2507
64
200Qwen3 30B A3B Instruct 2507
64
201Qwen3 30B A3B
64
212Qwen3 8B
61
223Qwen3 235B A22B
54
246Qwen3.8 Omni Flash
40
269Qwen3.8 Flash
40
280Qwen3.8 2.4T A95B
40
291Qwen3.7 Flash
40
328Qwen3.6 Flash
40
329Qwen3.6 35B A3B
40
330Qwen3.6 27B
40
344Qwen3 Coder Next
40
365Qwen3 VL 32B Instruct
40
367Qwen3 VL 8B Thinking
40
368Qwen3 VL 8B Instruct
40
369Qwen3 VL 30B A3B Thinking
40
370Qwen3 VL 30B A3B Instruct
40
371Qwen3 Coder Plus
40
372Qwen3 Coder Flash
40
373Qwen Plus 0728
40
380Qwen3 Coder 30B A3B Instruct
40
381Qwen3 Coder 480B A35B
40
390Qwen3 14B
40
391Qwen3 32B
40
401Qwen2.5 VL 72B Instruct
40
402Qwen-Plus
40
411Qwen2.5 Coder 32B Instruct
40
412Qwen2.5 72B Instruct
40
419Qwen2.5 7B Instruct
38
53 models

Scoreboard

排名模型评分
#88Qwen3.5 397B A17B79
#110Qwen3.5-122B-A10B78
#112Qwen3.5-27B77
#119Qwen3.5-35B-A3B76
#122Qwen3.8 Max (0902)76
#123Qwen3.7 Plus76
#129Qwen3.7 Max75
#130Qwen3.5 Plus 2026-04-2075
#131Qwen3.6 Max Preview75
#136Qwen3.6 Plus74
#141Qwen3.8 27B73
#145Qwen3.8 27B (free)73
#169Qwen3 VL 235B A22B Thinking69
#170Qwen3 VL 235B A22B Instruct69
#175Qwen3.5-Flash69
#177Qwen3.5 Plus 2026-02-1568
#178Qwen3 Max Thinking68
#182Qwen3 Max67
#185Qwen3 Next 80B A3B Thinking67
#186Qwen3 Next 80B A3B Instruct67
#188Qwen3.5-9B67
#195Qwen3 235B A22B Thinking 250765
#198Qwen3 235B A22B Instruct 250765
#199Qwen3 30B A3B Thinking 250764
#200Qwen3 30B A3B Instruct 250764
#201Qwen3 30B A3B64
#212Qwen3 8B61
#223Qwen3 235B A22B54
#246Qwen3.8 Omni Flash40
#269Qwen3.8 Flash40
#280Qwen3.8 2.4T A95B40
#291Qwen3.7 Flash40
#328Qwen3.6 Flash40
#329Qwen3.6 35B A3B40
#330Qwen3.6 27B40
#344Qwen3 Coder Next40
#365Qwen3 VL 32B Instruct40
#367Qwen3 VL 8B Thinking40
#368Qwen3 VL 8B Instruct40
#369Qwen3 VL 30B A3B Thinking40
#370Qwen3 VL 30B A3B Instruct40
#371Qwen3 Coder Plus40
#372Qwen3 Coder Flash40
#373Qwen Plus 072840
#380Qwen3 Coder 30B A3B Instruct40
#381Qwen3 Coder 480B A35B40
#390Qwen3 14B40
#391Qwen3 32B40
#401Qwen2.5 VL 72B Instruct40
#402Qwen-Plus40
#411Qwen2.5 Coder 32B Instruct40
#412Qwen2.5 72B Instruct40
#419Qwen2.5 7B Instruct38

类别分布

Coding
53

官方链接

APIDocumentation

相关

All providersCompare Alibaba modelsFull leaderboardPricing comparisonHow benchmarks workAll benchmarksHow to choose a modelAI model familiesCost optimization guideAPI integration guidePrice changesRank changesFull leaderboard
Frequently Asked Questions

Alibaba目前在我们平台上提供53个AI模型，平均质量评分为56/100。

Alibaba评分最高的模型是Qwen3.5 397B A17B，总排名第88名，综合评分79/100。

是的，Alibaba提供1个可免费使用的模型。

Alibaba模型的平均评分为56/100。他们最好的模型Qwen3.5 397B A17B全球排名第88名。访问我们的服务商对比页面进行详细分析。

Alibaba Models - Rankings, Pricing & Benchmarks (2026) | LM Market Cap