Intelligence index
Outperforms 38% of compared models
Qwen3 235B A22B Thinking 2507
Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144 tokens of context. This "thinking-only" variant enhances structured logical reasoning, mathematics, science, and long-form generation, showing strong benchmark performance across AIME, SuperGPQA, LiveCodeBench, and MMLU-Redux. It enforces a special reasoning mode (</think>) and is designed for high-token outputs (up to 81,920 tokens) in challenging domains.
The model is instruction-tuned and excels at step-by-step reasoning, tool use, agentic workflows, and multilingual tasks. This release represents the most capable open-source variant in the Qwen3-235B series, surpassing many closed models in structured reasoning use cases.
- Input / output price
- $0.45/$3.5per 1M tokens
- Context
- 128K
- Released
- 2025-07-25
Pricing
Artificial Analysis
Explore rankingsCoding index
Outperforms 22% of compared models
Agentic index
Outperforms 22% of compared models
Design Arena
Elo scores and win rates across design and agent tasks.
Category performance
1,000-1,500 EloModel Arena
3D
995Elo
Win rate 40.4%
Code Categories
1031Elo
Win rate 40.8%
Data Visualization
950Elo
Win rate 32.6%
Website
1051Elo
Win rate 42%
UI Component
940Elo
Win rate 34%
Game Development
957Elo
Win rate 34.2%
Related Models
Qwen3.8 Max (0902)
qwenQwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text, with a 1M-token context window and reasoning enabled by default. This snapshot is post-trained for coding and agentic work, including multi-step software projects, multi-tool orchestration, and long-horizon task execution. It also targets chart reasoning, document parsing, and multimodal understanding over long documents and extended video. Tool calling, structured outputs, and configurable reasoning effort are supported.
- Context
- 1.0M
- Max output
- 131.1K
- Released
- 2026-09-03
- Input
- $2/M
- Output
- $6/M
- Cache read
- $0.25/M
Qwen3.8 2.4T A95B
qwenQwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of Qwen3.8 Max, with 95 billion active parameters out of 2.4 trillion total. It is suited for coding, research, complex reasoning, and agentic workflows.
- Context
- 1.0M
- Max output
- 909K
- Released
- 2026-08-12
- Input
- $2/M
- Output
- $6/M
- Cache read
- $0.25/M
Qwen3.8 27B
qwenQwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be enabled or disabled.
- Context
- 1.0M
- Max output
- 65.5K
- Released
- 2026-08-14
- Input
- $0.039/M
- Output
- $1.25/M
- Cache read
- $0.0039/M