Qwen3-235B-A22B
Qwen3-235B-A22B is an AI model published by 阿里巴巴, released on 2025-04-28, for 推理大模型, with 2350.0B parameters, and 128K tokens context length, requiring about 470GB storage, under the Apache 2.0 license.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
| Modality | Input | Output |
|---|---|---|
| Text | $0.7 | $8.4 |
Qwen3-235B-A22B currently shows benchmark results led by GSM8K (2 / 26, score 96.40), MATH-500 (7 / 43, score 98), AIME 2024 (20 / 62, score 85.70). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.
Qwen3-235B-A22B是阿里开源的第三代千问大模型最大参数规模的版本，共2350亿参数，但是这是MoE（混合专家）架构的大模型，每次推理仅激活其中的220亿参数。
欢迎关注 DataLearner 官方微信，获得最新 AI 技术推送
