Toggle navigation

Alibaba

Available in Shortly AI

Qwen3-30B-A3B

Released April 28, 2025

ReasoningTool Use

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support

Context window
41K tokens
Maximum output
16.4K tokens
Input pricing
$0.12/M
Output pricing
$0.50/M

Independent benchmark

LiveBench historical snapshot

39.0overall

Historical benchmark data from LiveBench, release 2026-01-08. Scores are pinned and are not fetched on page load.

Qwen3-30B-A3B LiveBench category scores
CategoryScore
Reasoning36.678
Coding48.883
Agentic Coding1.667
Mathematics65.347
Data Analysis44.923
Language54.465
Instruction Following21.108

Benchmarks measure selected evaluation tasks and do not guarantee performance for every prompt or workflow.

FAQ

Similar AI models

Available with one subscription

Start with Qwen3-30B-A3B in Shortly AI

Keep your conversations, files and model choices together in one workspace.