Qwen3.5 35B A3B (Reasoning)
Intelligence
37.1
#111/521
Coding
30.3
#129/427
Math
—
Speed
150 tok/s
TTFT: 1.02s
Pricing
$0.25 / $2.00
per 1M tokens (in/out)
Qwen3.5-35B-A3B is a multimodal Mixture-of-Experts model with 35 billion total parameters and 3 billion activated parameters. It combines strong reasoning, coding, agentic, and visual understanding performance with production-friendly efficiency and a native 262K context window.
Qwen3.5 35B A3B (Reasoning) is Alibaba’s advanced language model designed for reasoning tasks. It processes at 149.837 tokens per second and is priced at $0.25 per million input tokens, targeting professional users.
When to Use Qwen3.5 35B A3B (Reasoning)
✓ Best For
- Natural language understanding and reasoning tasks.
- Coding assistance and debugging.
- Data analysis and interpretation.
✗ Not Ideal For
- High-complexity mathematical problem solving.
- Real-time applications requiring ultra-low latency.
How Qwen3.5 35B A3B (Reasoning) Compares
Intelligence Index · Higher is better
AlibabaAnthropicDeepSeekChina Mobile
Benchmark Profile
Coding Index
AlibabaAmazonZ AIAnthropic
Output Speed · tok/s
KimiAlibabaXiaomiOpenAI
Intelligence · Coding · Math
Intelligence
Coding
Math
All Benchmark Scores (9)
| Benchmark | Score | |
|---|---|---|
| Intelligence Index | 37.1 | |
| Coding Index | 30.3 | |
| GPQA | 845% | |
| HLE | 197% | |
| SciCode | 37.7% | |
| IFBench | 72.5% | |
| LCR | 62.7% | |
| TerminalBench Hard | 26.5% | |
| Tau2 | 89.2% |
Data: Artificial Analysis · Updated: April 10, 2026
Frequently Asked Questions (15)
When was Qwen3.5 35B A3B (Reasoning) released?
Qwen3.5 35B A3B (Reasoning) was released on February 24, 2026.
Who created Qwen3.5 35B A3B (Reasoning)?
Qwen3.5 35B A3B (Reasoning) was created by Alibaba.
How intelligent is Qwen3.5 35B A3B (Reasoning)?
Qwen3.5 35B A3B (Reasoning) scores 37 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 15).
How fast is Qwen3.5 35B A3B (Reasoning)?
Qwen3.5 35B A3B (Reasoning) generates output at 180.7 tokens per second (based on Alibaba's API), which is well above average compared to other open weight models of similar size (median: 96.9 t/s).
What is the latency of Qwen3.5 35B A3B (Reasoning)?
Qwen3.5 35B A3B (Reasoning) has a time to first token (TTFT) of 2.07s (based on Alibaba's API), which is somewhat higher than average compared to other open weight models of similar size (median: 1.90s).
How much does Qwen3.5 35B A3B (Reasoning) cost?
Qwen3.5 35B A3B (Reasoning) costs $0.25 per 1M input tokens (somewhat higher than average, median: $0.18) and $2.00 per 1M output tokens (at the higher end, median: $0.40), based on Alibaba's API.
What is Qwen3.5 35B A3B (Reasoning) API pricing?
Qwen3.5 35B A3B (Reasoning) costs $0.25 per 1M input tokens and $2.00 per 1M output tokens (based on Alibaba's API). For a blended rate (3:1 input to output ratio), this is $0.69 per 1M tokens. Pricing may vary by provider.
How verbose is Qwen3.5 35B A3B (Reasoning)?
When evaluated on the Intelligence Index, Qwen3.5 35B A3B (Reasoning) generated 100M output tokens, which is at the higher end compared to other open weight models of similar size (median: 23M).
Is Qwen3.5 35B A3B (Reasoning) a reasoning model?
Yes, Qwen3.5 35B A3B (Reasoning) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
What input modalities does Qwen3.5 35B A3B (Reasoning) support?
Qwen3.5 35B A3B (Reasoning) supports text and image input.
What output modalities does Qwen3.5 35B A3B (Reasoning) support?
Qwen3.5 35B A3B (Reasoning) supports text output.
Can Qwen3.5 35B A3B (Reasoning) process images?
Yes, Qwen3.5 35B A3B (Reasoning) supports image input and can analyze, describe, and answer questions about images.
Is Qwen3.5 35B A3B (Reasoning) multimodal?
Yes, Qwen3.5 35B A3B (Reasoning) is multimodal. It can process text and image input and generate text output.
What is the context window of Qwen3.5 35B A3B (Reasoning)?
Qwen3.5 35B A3B (Reasoning) has a context window of 260k tokens. This determines how much text and conversation history the model can process in a single request.
Is Qwen3.5 35B A3B (Reasoning) open source?
Yes, Qwen3.5 35B A3B (Reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
