Qwen3 235B A22B Thinking moves to version Qwen3-235B-A22B-Thinking-2507

The OnAirToday AI Progress Tracker recorded a verified change to Alibaba's Qwen3 235B A22B Thinking (version Qwen3-235B-A22B-Thinking-2507): Version now Qwen3-235B-A22B-Thinking-2507 (was Qwen3-235B-A22B-Thinking).

Alibaba's Qwen3-235B-A22B-Thinking-2507 is an open-weight, text-only reasoning model with 235 billion total parameters, 22 billion active parameters and a native 262,144-token context window. It targets mathematics, scientific reasoning and coding; newer Qwen3-Next models have shipped, but this remains a distinct thinking-only checkpoint.

What changed in this review:

• The exact release identifier is Qwen3-235B-A22B-Thinking-2507.
• Native context length is documented as 262,144 tokens.
• Vendor results document GPQA Diamond at 81.1%, AIME 2025 at 92.3%, and LiveCodeBench v6 at 74.1%.
• Qwen3-Next-80B-A3B-Thinking has shipped as a newer Qwen3-family model.
• Capability score 57 → 73
• Flaws and limitations updated

Teams building on Qwen3 235B A22B Thinking should confirm limits, pricing and benchmark coverage against the vendor's own documentation before relying on these figures.

The full profile — capabilities, benchmark citations, known flaws and risk guidance — is on the tracker at /ai-models/qwen3-235b-a22b-thinking.

References:

• https://huggingface.co/Qwen/Qwen3-235B-A22B-Thinking-2507
• https://huggingface.co/Qwen/Qwen3-235B-A22B
• https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Thinking