Qwen: Qwen3.5-35B-A3B
Analysis Summary
Qwen3.5-35B-A3B is a mixture-of-experts model from Alibaba's Qwen family, activating 3B parameters from a 35B total. Its intelligence index of 23.4 and coding index of 16.8 reflect modest capability for its parameter count, and its ifbench score of 0.445 is low, suggesting inconsistent instruction following. It does support text, image, and video inputs alongside tool use and function calling, and its 262K context window is generous.
For businesses, it is best suited to cost-sensitive, moderate-complexity tasks where multimodal input is useful but deep reasoning is not required. Its agentic index of 48.4 is adequate for basic tool workflows, but the weak instruction following limits reliability in structured output scenarios. Coding tasks are not a strong fit.
At $0.14 input and $1.00 output per million tokens, it is cheap but not the most efficient option in its tier. A -4 point regional penalty applies. Teams prioritising cost and multimodal coverage over reasoning depth may find it useful, but Qwen3.5-27B or Qwen3.5-9B offer better capability-to-cost ratios within the same family.
Assessed June 17, 2026
Editorial notes
Qwen3.5-35B-A3B is a sparse MoE model with vision and video support, tool use, and a 262K context window at very low cost, though its coding index is limited and instruction following is below average for its tier.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How Qwen: Qwen3.5-35B-A3B compares
Qwen: Qwen3.5-35B-A3B ranks #113 of 380 AI models we track for overall intelligence, #167 of 317 for coding, #94 of 292 for agentic tasks. Its 262K-token context window is larger than 81% of the models we list. At $0.14 per million input tokens it is cheaper than 58% of comparable models.
About Qwen: Qwen3.5-35B-A3B
The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall..
Capabilities
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Qwen: Qwen3.5-35B-A3B stack up?
Compare side-by-side with other professional models.
Model Information
| OpenRouter ID |
qwen/qwen3.5-35b-a3b
|
| Provider | qwen |
| Release Date | February 25, 2026 |
| Context Length | 262,144 tokens |
| Max Completion | 81,920 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.14 | $0.000140 |
| Output | $1.00 | $0.001000 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about Qwen: Qwen3.5-35B-A3B
How much does Qwen: Qwen3.5-35B-A3B cost?
Qwen: Qwen3.5-35B-A3B costs $0.14 per million input tokens and $1.00 per million output tokens.
What is the context window of Qwen: Qwen3.5-35B-A3B?
Qwen: Qwen3.5-35B-A3B has a context window of 262,144 tokens (262K).
Is Qwen: Qwen3.5-35B-A3B good for coding?
On our coding benchmark index, Qwen: Qwen3.5-35B-A3B ranks #167 of 317 models, placing it in the broader range of the field for code generation and debugging.
What can Qwen: Qwen3.5-35B-A3B do?
Qwen: Qwen3.5-35B-A3B supports image/vision input, tool use, and function calling.
Who created Qwen: Qwen3.5-35B-A3B?
Qwen: Qwen3.5-35B-A3B is developed by Qwen and was released on February 25, 2026.
