Qwen3 30B A3B Thinking 2507

In one line

Qwen3 30B A3B Thinking 2507 by Alibaba, measured by Artificial Analysis at 9.8 on the Intelligence Index, 12.1 on coding and 0.9 on agentic work. Added to WhichAI automatically from live data on October 3, 2026: no editorial review yet, so judge it by the numbers, not by a verdict. OpenRouter's description: “Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking.”

Alternatives worth a look

• Mistral Large 3 (Mistral AI) · AA 9.3Open weights · Le Chat free tier · API
• Qwen3 Coder Next (Alibaba) · AA 9.2API $0.12/$0.8 per 1M tokens on OpenRouter · open weights · listed February 4, 2026
• gpt-oss-20b (OpenAI) · AA 9Open weights · runs on a laptop

Artificial Analysis Intelligence Index, official scale (the number published on artificialanalysis.ai), relayed by OpenRouter and refreshed automatically: last read October 3, 2026. 97 models carry a current official measurement. A value marked ~ is converted from an earlier snapshot because no current measurement is published; an unmeasured model is never ranked. Context, price, modality and listing dates come from the public OpenRouter model list (refreshed automatically on the live site; static copy retrieved October 3, 2026) and vendor pages. Missing values are not published or not yet verified - shown as -. Sources are linked inside the app (Model guide and About > Methodology).