Qwen3-235B-A22B-Thinking-2507
Alibaba's 235B MoE reasoning flagship: 22B active, 256K context, Apache 2.0.
About
Qwen3-235B-A22B-Thinking-2507 is Alibaba's July 2025 reasoning-focused flagship, a 235B-parameter mixture-of-experts that activates only 22B parameters per token, released under Apache 2.0.
The thinking variant defaults to deep reasoning mode for math, science, coding and logic tasks, with native 256K context for extended chains of thought. Analysts reported 92.3 on AIME25, near proprietary frontier systems.
Trained on 36 trillion tokens across 119 languages, it became one of the most downloaded open reasoning checkpoints on Hugging Face and ModelScope.
Specs
Context window
Pricing
Free quota
API access
Weights
Released
Benchmarks
Provider-reported unless a source says otherwise. Benchmarks are marketing-adjacent by nature — treat them as directional.
Use cases
Trust score — 9/10
Scored 9/10 (verified tier, metrics-v1). Evidence: Verified via vendor site/docs/GitHub and reputable coverage, wave 116; Trending score 86/100 from researcher assessment.
More in the qwen3 family
- Qwen3-32B-AWQ
- Qwen3-Next-80B-A3B
- Qwen3-235B-A22B
- Qwen3-235B-A22B-2507
- Qwen3-4B-Instruct-2507
- Qwen3-8B
- Qwen3.5
- Qwen3-235B-A22B-Instruct-2507
- Qwen3 235B
- Qwen3-Omni-Flash
- Qwen3.6-27B
- Qwen3-32B
- Qwen3-Max
- Qwen3.8-Flash-Next
- Qwen3-Coder-Plus
- Qwen3
- Qwen3-0.6B
- Qwen3-4B
- Qwen3-Coder-Next
- Qwen3-4B-2507
- Qwen3-14B
- Qwen3-VL-30B-A3B
- Qwen3-1.7B
- Qwen3-Omni-30B-A3B