Qwen Models
Qwen logo

Qwen3 235B A22B Instruct 2507

235B

byQwen

Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...

Input Price$0.40/1M tokens
Output Price$2.15/1M tokens
Intelligence29.5
Coding23.2

Specifications

Technical details and pricing.

ProviderQwen
Context Window262,144 tokens
Release DateJul 25, 2025
ModalitiesText

Benchmarks

12 benchmark scores from Artificial Analysis.

GPQA79.0%
MMLU Pro84.3%
HLE15.0%
LiveCodeBench78.8%
MATH 50098.4%
AIME 202591.0%
AIME94.0%
SciCode42.4%
LCR67.0%
IFBench51.2%
Tau253.2%
TerminalBench Hard13.6%

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 Instruct 2507 good for?

Use Qwen3 235B A22B Instruct 2507 for everyday tasks like writing, summarizing, brainstorming, and getting clear explanations.

How much does Qwen3 235B A22B Instruct 2507 cost?

Pricing is based on usage. Current rates are $0.40/1M tokens for input and $2.15/1M tokens for output.

Can I try Qwen3 235B A22B Instruct 2507 for free?

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

Does Qwen3 235B A22B Instruct 2507 support images or audio?

Qwen3 235B A22B Instruct 2507 focuses on text-based tasks.

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