Model Tracker
Qwen3-32B
Qwen3-32B is an AI model made by Alibaba Tongyi. Alibaba Tongyi released it on 29 April 2025. It is generally available. It takes text and returns text.
Qwen3-32B is an AI model made by Alibaba Tongyi. Alibaba Tongyi released it on 29 April 2025. It is generally available. It takes text and returns text. Its context window is 32,768 tokens. Its weights are open.
- Released
- 29 April 2025 — qwenlm.github.io, read 16 October 2026
- Status
- Generally available — help.aliyun.com, read 16 October 2026
- Takes
- Text — huggingface.co, read 16 October 2026
- Returns
- Text — huggingface.co, read 16 October 2026
- Open weights
- Yes — qwenlm.github.io, read 16 October 2026
- Licence
- Not confirmed: two readings disagree: Apache 2.0 and apache-2.0
- Context window
- 32,768 tokens — huggingface.co, read 16 October 2026
- Longest answer
- Not confirmed: The maker gives generation examples and output-length recommendations, but the pages reviewed do not state a standard maximum output limit for Qwen3-32B.
- Knowledge cutoff
- Not confirmed: The maker's model card and release page reviewed do not state a knowledge-cutoff date for Qwen3-32B.
- API price, input
- Not confirmed: its line was not found on its page, and a second reading did not confirm it
- API price, output
- Not confirmed: its line was not found on its page, and a second reading did not confirm it
- Where
- Not confirmed: two readings disagree: api, weights and weights
- Parameters
- Not confirmed: the figure is not printed in its sentence (a sum or a figure the page does not give)
- Model card
- https://huggingface.co/Qwen/Qwen3-32B — huggingface.co, read 16 October 2026
Benchmarks
Measured by others, not by the maker: each score with the name the measurer gives the model and the setting it ran, its day and its licence.
Arena
- Text Arena, qwen3-32b: 1,347 (1,337–1,356, 3,926 votes), published 15 October 2026
Arena’s leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0: ratings from people’s votes between two anonymous models, as Arena publishes them. Data · CC BY 4.0
Epoch AI
- Epoch Capabilities Index, Qwen3-32B: 138.5 (134.8–140.4), as of 19 October 2026
- GPQA Diamond, Qwen3-32B: 65.7% (± 2.8), run 28 August 2026
- GPQA Diamond, Qwen3-32B_none: 54.1% (± 2.8), run 30 August 2026
- OTIS Mock AIME 2024–2025, Qwen3-32B: 66.9% (± 6.0), run 30 August 2026
- OTIS Mock AIME 2024–2025, Qwen3-32B_none: 23.1% (± 5.1), run 30 August 2026
Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks, CC BY 4.0: Epoch AI’s own runs and its Capabilities Index. Data · CC BY 4.0
Questions
When was Qwen3-32B released?
Alibaba Tongyi released Qwen3-32B on 29 April 2025.
Is Qwen3-32B still available?
Yes: it is generally available, as Alibaba Tongyi states it.
What is the context window of Qwen3-32B?
The context window of Qwen3-32B is 32,768 tokens, as Alibaba Tongyi prints it.
Are the weights of Qwen3-32B open?
Yes: Alibaba Tongyi publishes the weights of Qwen3-32B for download.
What does Qwen3-32B take and return?
Qwen3-32B takes text and returns text.
More from Alibaba Tongyi
- Qwen-1.8B
- Qwen-14B
- Qwen-72B
- Qwen-7B
- Qwen-Audio
- Qwen-Image
- Qwen-VL
- Qwen-VL-Max
- Qwen-VL-Plus
- Qwen1.5-MoE-A2.7B
- Qwen2-Audio
- Qwen2-VL-72B
- Qwen2.5-Omni-3B
- Qwen2.5-Omni-7B
- Qwen2.5-VL-3B
- Qwen2.5-VL-7B
- Qwen3-0.6B
- Qwen3-1.7B
- Qwen3-14B
- Qwen3-235B-A22B
- Qwen3-30B-A3B
- Qwen3-4B
- Qwen3-8B
- Qwen3-ASR-0.6B
Sources
- Qwen3: Think Deeper, Act Faster (read 16 October 2026)
- Qwen/Qwen3-32B (read 16 October 2026)
- Alibaba Cloud Model Studio model pricing (read 16 October 2026)
- Qwen3/docs/source/getting_started/concepts.md (read 16 October 2026)