Qwen Models
Qwen logo

Qwen3 235B A22B

235B

byQwen

Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for complex reasoning, math, and...

Input Price$0.70/1M tokens
Output Price$8.40/1M tokens
Intelligence19.8
Coding17.4

Specifications

Technical details and pricing.

ProviderQwen
Context Window131,072 tokens
Release DateApr 28, 2025
ModalitiesText

Benchmarks

12 benchmark scores from Artificial Analysis.

GPQA70.0%
MMLU Pro82.8%
HLE11.7%
LiveCodeBench62.2%
MATH 50093.0%
AIME 202582.0%
AIME84.0%
SciCode39.9%
LCR0.0%
IFBench38.7%
Tau224.0%
TerminalBench Hard6.1%

Composite Indices

Higher is better; speed and price are normalized

Standard Benchmarks

Only benchmarks with data are shown

Frequently Asked Questions

What is Qwen3 235B A22B good for?

Use Qwen3 235B A22B for everyday tasks like writing, summarizing, brainstorming, and getting clear explanations.

How much does Qwen3 235B A22B cost?

Pricing is based on usage. Current rates are $0.70/1M tokens for input and $8.40/1M tokens for output.

Can I try Qwen3 235B A22B for free?

Yes. You can start a chat instantly and test the model before deciding on a plan.

Does Qwen3 235B A22B support images or audio?

Qwen3 235B A22B focuses on text-based tasks.

Benchmarks and pricing use Artificial Analysis where available. Catalog specs are used as a fallback.