Qwen: Qwen3.6 35B A3B
Analysis Summary
Qwen: Qwen3.6 35B A3B sits in the Specialist tier on our leaderboard, ranked #65 of 525 published models on overall intelligence. At $0.161 input and $0.965 output per 1M tokens, it is among the most expensive on the market. It offers a generous context window for extended reasoning and code review and supports vision and reasoning.
Editorial notes
Qwen3.6 35B A3B (Reasoning) from Alibaba hits the 43-point intelligence floor with strong agentic, instruction-following, and long-context scores; the -4 regional penalty applies, capping its practical score for Western deployments.
Assessed April 26, 2026
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated..
Capabilities
Performance Indices
Source: Artificial Analysis
This model was released recently. Independent benchmark evaluations are typically completed within days of release — these figures are preliminary and are likely to be updated as testing is finalised.
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Qwen: Qwen3.6 35B A3B stack up?
Compare side-by-side with other specialist models.
Model Information
| OpenRouter ID |
qwen/qwen3.6-35b-a3b
|
| Provider | qwen |
| Release Date | April 27, 2026 |
| Context Length | 262,144 tokens |
| Max Completion | 65,536 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.16 | $0.000161 |
| Output | $0.97 | $0.000965 |
Live Performance
Live endpoint metrics — refreshed every 30 minutes.
