Simon Willison’s Weblog

Qwen3-235B-A22B-Thinking-2507 (via) The third Qwen model release week, following Qwen3-235B-A22B-Instruct-2507 on Monday 21st and Qwen3-Coder-480B-A35B-Instruct on Tuesday 22nd.

Those two were both non-reasoning models - a change from the previous models in the Qwen 3 family which combined reasoning and non-reasoning in the same model, controlled by /think and /no_think tokens.

Today's model, Qwen3-235B-A22B-Thinking-2507 (also released as an FP8 variant), is their new thinking variant.

Qwen claim "state-of-the-art results among open-source thinking models" and have increased the context length to 262,144 tokens - a big jump from April's Qwen3-235B-A22B which was "32,768 natively and 131,072 tokens with YaRN".

Their own published benchmarks show comparable scores to DeepSeek-R1-0528, OpenAI's o3 and o4-mini, Gemini 2.5 Pro and Claude Opus 4 in thinking mode.

The new model is already available via OpenRouter.

But how good is its pelican?

I tried it with "Generate an SVG of a pelican riding a bicycle" via OpenRouter, and it thought for 166 seconds - nearly three minutes! I have never seen a model think for that long. No wonder the documentation includes the following:

However, since the model may require longer token sequences for reasoning, we strongly recommend using a context length greater than 131,072 when possible.

Here's a copy of that thinking trace. It was really fun to scan through:

The finished pelican? Not so great! I like the beak though:

# 10:52 pm / ai, generative-ai, llms, qwen, pelican-riding-a-bicycle, llm-reasoning, llm-release, ai-in-china