Model vendor
Alibaba Cloud / Qwen Team
The Qwen Team from Alibaba Cloud, developing the Qwen series of large language models including state-of-the-art mixture-of-experts and thinking-enabled models
Updated Aug 10, 2026. Data as of 2026-08-07
Published models48
Published versions51
Open defaults13
CountryCN
Alibaba Cloud / Qwen Team models
Default-version specifications and scored-version capability values are labeled separately.
| AC | Qwen3.7 Max | 90.3 | 80.0% | 1M | Closed weights | Qwen3.7 Max | |
| AC | Qwen3.5-397B-A17B | 75.2 | 100.0% | 262.1K | Open weights | Qwen3.5-397B-A17B | |
| AC | Qwen3.7-Plus | 73.1 | 80.0% | 1M | Closed weights | Qwen3.7-Plus | |
| AC | Qwen3.6 Plus | 72.4 | 80.0% | 1M | Closed weights | Qwen3.6 Plus | |
| AC | Qwen3.6-27B | 72.2 | 80.0% | 262.1K | Open weights | Qwen3.6-27B | |
| AC | Qwen3-235B-A22B-Thinking-2507 | 65.7 | 80.0% | 262.1K | Closed weights | Qwen3-235B-A22B-Thinking-2507 | |
| AC | Qwen3.5-122B-A10B | 61.4 | 100.0% | 262.1K | Open weights | Qwen3.5-122B-A10B | |
| AC | Qwen3 VL 235B A22B Thinking | 58.5 | 60.0% | 262.1K | Closed weights | Qwen3 VL 235B A22B Thinking | |
| AC | Qwen3.5-27B | 57.1 | 100.0% | 262.1K | Open weights | Qwen3.5-27B | |
| AC | Qwen2.5 32B Instruct | 56.9 | 80.0% | N/A | Closed weights | Qwen2.5 32B Instruct | |
| AC | Qwen3-Next-80B-A3B-Thinking | 54.1 | 80.0% | 131.1K | Open weights | Qwen3-Next-80B-A3B-Thinking | |
| AC | Qwen3.5-35B-A3B | 53.3 | 100.0% | 262.1K | Open weights | Qwen3.5-35B-A3B | |
| AC | Qwen2.5 72B Instruct | 53.1 | 80.0% | 131.1K | Closed weights | Qwen2.5 72B Instruct | |
| AC | Qwen3 VL 32B Thinking | 51.7 | 60.0% | N/A | Closed weights | Qwen3 VL 32B Thinking | |
| AC | Qwen2.5 VL 32B Instruct | 51.5 | 80.0% | N/A | Closed weights | Qwen2.5 VL 32B Instruct | |
| AC | Qwen3-235B-A22B-Instruct-2507 | 49.0 | 80.0% | 262.1K | Open weights | Qwen3-235B-A22B-Instruct-2507 | |
| AC | Qwen3.6-35B-A3B | 48.2 | 80.0% | 262.1K | Open weights | Qwen3.6-35B-A3B | |
| AC | Qwen2.5-Coder 32B Instruct | 45.4 | 80.0% | 128K | Closed weights | Qwen2.5-Coder 32B Instruct | |
| AC | Qwen2.5 14B Instruct | 43.9 | 80.0% | N/A | Closed weights | Qwen2.5 14B Instruct | |
| AC | Qwen3 VL 235B A22B Instruct | 42.7 | 60.0% | 262.1K | Closed weights | Qwen3 VL 235B A22B Instruct | |
| AC | Qwen3-Next-80B-A3B-Instruct | 41.8 | 80.0% | 131.1K | Open weights | Qwen3-Next-80B-A3B-Instruct | |
| AC | Qwen3 VL 30B A3B Thinking | 40.3 | 80.0% | 262.1K | Closed weights | Qwen3 VL 30B A3B Thinking | |
| AC | Qwen3 Max | 40.3 | 60.0% | 262.1K | Closed weights | Qwen3 Max | |
| AC | Qwen3 30B A3B | 39.7 | 60.0% | 128K | Closed weights | Qwen3 30B A3B | |
| AC | Qwen2 72B Instruct | 38.0 | 80.0% | N/A | Closed weights | Qwen2 72B Instruct | |
| AC | Qwen3.5-9B | 36.1 | 80.0% | 262.1K | Open weights | Qwen3.5-9B | |
| AC | Qwen3 VL 32B Instruct | 36.0 | 60.0% | N/A | Closed weights | Qwen3 VL 32B Instruct | |
| AC | Qwen3 VL 8B Thinking | 32.9 | 80.0% | 262.1K | Closed weights | Qwen3 VL 8B Thinking | |
| AC | QwQ-32B | 32.6 | 80.0% | N/A | Closed weights | QwQ-32B | |
| AC | Qwen2.5 7B Instruct | 32.4 | 80.0% | 131.1K | Closed weights | Qwen2.5 7B Instruct | |
| AC | Qwen3.5-4B | 28.0 | 80.0% | N/A | Closed weights | Qwen3.5-4B | |
| AC | Qwen3 VL 30B A3B Instruct | 25.0 | 80.0% | 262.1K | Closed weights | Qwen3 VL 30B A3B Instruct | |
| AC | Qwen2.5-Coder 7B Instruct | 24.4 | 80.0% | N/A | Closed weights | Qwen2.5-Coder 7B Instruct | |
| AC | Qwen3 VL 4B Thinking | 23.8 | 80.0% | 262.1K | Closed weights | Qwen3 VL 4B Thinking | |
| AC | Qwen2.5-Omni-7B | 20.7 | 80.0% | N/A | Closed weights | Qwen2.5-Omni-7B | |
| AC | Qwen3.5-2B | 16.8 | 60.0% | N/A | Closed weights | Qwen3.5-2B | |
| AC | Qwen2 7B Instruct | 15.1 | 80.0% | N/A | Closed weights | Qwen2 7B Instruct | |
| AC | Qwen3 VL 8B Instruct | 12.6 | 60.0% | 262.1K | Closed weights | Qwen3 VL 8B Instruct | |
| AC | Qwen3 VL 4B Instruct | 7.7 | 60.0% | 262.1K | Closed weights | Qwen3 VL 4B Instruct | |
| AC | Qwen3.5-0.8B | 0.3 | 60.0% | N/A | Closed weights | Qwen3.5-0.8B | |
| AC | QvQ-72B-Preview | N/A | N/A | N/A | Closed weights | Not scored | |
| AC | Qwen2-VL-72B-Instruct | N/A | N/A | N/A | Closed weights | Not scored | |
| AC | Qwen2.5 VL 72B Instruct | N/A | N/A | 131.1K | Open weights | Not scored | |
| AC | Qwen2.5 VL 7B Instruct | N/A | N/A | N/A | Closed weights | Not scored | |
| AC | Qwen3 32B | N/A | N/A | 131.1K | Open weights | Not scored | |
| AC | Qwen3-Coder | N/A | N/A | 256K | Closed weights | Not scored | |
| AC | Qwen3-Coder 480B A35B Instruct | N/A | N/A | 262.1K | Open weights | Not scored | |
| AC | Qwen3.8 Max | N/A | N/A | 1M | Closed weights | Not scored |
Alibaba Cloud / Qwen Team capability scores
Each unique model uses its latest scored version.
Alibaba Cloud / Qwen Team highlights
Leaders from this vendor's current published catalog.
Top scoreQwen3.7 Max90.3 LLMBoardLowest official inputQwen2.5 Omni 7B$0.10 / 1MLargest contextQwen3.6 Plus1M tokens
Open-weight defaults13of 48 published models
What is Alibaba Cloud / Qwen Team?
Vendor context from the published model registry.
The Qwen Team from Alibaba Cloud, developing the Qwen series of large language models including state-of-the-art mixture-of-experts and thinking-enabled models
Model ownership is separate from API hosting. One model can be offered by multiple API providers with different prices.
- Vendor
- Alibaba Cloud / Qwen Team
- Published models
- 48
- Published versions
- 51
- Country
- CN
- Founded
- Not published
Vendor description and inventory come from the published model registry.
FAQ
Common questions about Alibaba Cloud / Qwen Team.
What is Alibaba Cloud / Qwen Team's highest-ranked model?
Qwen3.7 Max currently has the strongest published LLMBoard score from this vendor.
How many Alibaba Cloud / Qwen Team models are tracked?
The current public catalog contains 48 independently selectable Alibaba Cloud / Qwen Team model products and 51 published versions.
Does Alibaba Cloud / Qwen Team host every listed model API?
Not necessarily. Vendor identifies the model developer; API providers are tracked separately.
Does Alibaba Cloud / Qwen Team publish open-weight models?
13 current default versions are marked as open weight.