# Qwen: Qwen3.5 35B A3B: AI model fact sheet

- **Provider:** qwen
- **Released:** 2026-02-25
- **Context window:** 262,144 tokens
- **Parameters:** 35B (3B active)
- **API pricing:** $0.25 / 1M input, $2.00 / 1M output
- **OpenRouter ID:** qwen/qwen3.5-35b-a3b
- **Capabilities:** conversation, reasoning, code-generation, analysis, tool-use, agentic-tool-use, translation

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 performance is comparable to that of the Qwen3.5-27B.

## Benchmarks

| Benchmark | Score |
| --- | --- |
| MMLU-Pro | 85.3 |
| GPQA Diamond | 84.2% |
| SWE-bench Verified | 69.2% |
| LiveCodeBench v6 | 74.6 |
| HMMT Feb 25 | 89.0% |

Source: real side-by-side outputs, pricing and specs at https://rival.tips/models/qwen3.5-35b-a3b