Qwen3 235B A22B Thinking: newer Qwen3-Next thinking models have shipped; this profile remains specific to Qwen3-235B-A22B-Thinking-2507
A version-specific profile for Qwen3-235B-A22B-Thinking-2507
Newer Qwen3-Next thinking models have shipped; this profile remains specific to Qwen3-235B-A22B-Thinking-2507 — verified by the OnAirToday AI Progress Tracker against Alibaba's published documentation.
OnAirToday
Newsroom
The OnAirToday AI Progress Tracker recorded a verified change to Alibaba's Qwen3 235B A22B Thinking (version Qwen3-235B-A22B-Thinking-2507): Newer Qwen3-Next thinking models have shipped; this profile remains specific to Qwen3-235B-A22B-Thinking-2507.
Alibaba's Qwen3-235B-A22B-Thinking-2507 is an open-weight, text-only reasoning model with 235 billion total parameters and 22 billion activated per token. This thinking-only checkpoint supports a native 262,144-token context and targets mathematical reasoning, scientific questions, coding and long-document analysis.
What changed in this review:
- Benchmark labels distinguish AIME 2025 and LiveCodeBench v6.
- Capability score 64 → 73
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
Generated insight by OnAirToday AI
The note distinguishes this profile from newer Qwen3-Next thinking models, helping readers avoid conflating model versions. Its scope is stated as verified against Alibaba's published documentation.

Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.