Qwen3.5 2B (Non-reasoning)
Intelligence
14.7
#348/523
Coding
4.9
#382/429
Math
—
Speed
—
Pricing
—
Qwen3.5-2B is a 2 billion parameter vision-language model using Gated DeltaNet hybrid architecture with a 3:1 ratio of linear attention to full softmax attention. It supports 262K native context length and features both thinking and non-thinking modes.
Qwen3.5 2B (Non-reasoning) is Alibaba’s language model designed for various natural language processing tasks. It has an Intelligence Index of 14.7, indicating its capabilities in understanding and generating human-like text. This model is suitable for professional users seeking advanced text generation solutions.
When to Use Qwen3.5 2B (Non-reasoning)
✓ Best For
- Natural language understanding tasks.
- Text generation for content creation.
- Assisting in automated customer support.
✗ Not Ideal For
- Complex reasoning tasks.
- High-level mathematical computations.
How Qwen3.5 2B (Non-reasoning) Compares
Intelligence Index · Higher is better
NVIDIAIBMAlibabaGoogle
Benchmark Profile
Coding Index
InclusionAIIBMAlibabaMetaMistral
Intelligence · Coding · Math
Intelligence
Coding
Math
All Benchmark Scores (9)
| Benchmark | Score | |
|---|---|---|
| Intelligence Index | 14.7 | |
| Coding Index | 4.9 | |
| GPQA | 438% | |
| HLE | 49% | |
| SciCode | 7.2% | |
| IFBench | 29.1% | |
| LCR | 13.7% | |
| TerminalBench Hard | 3.8% | |
| Tau2 | 81.6% |
Data: Artificial Analysis · Updated: March 27, 2026
Frequently Asked Questions (15)
When was Qwen3.5 2B (Non-reasoning) released?
Qwen3.5 2B (Non-reasoning) was released on March 2, 2026.
Who created Qwen3.5 2B (Non-reasoning)?
Qwen3.5 2B (Non-reasoning) was created by Alibaba.
How intelligent is Qwen3.5 2B (Non-reasoning)?
Qwen3.5 2B (Non-reasoning) scores 15 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight non-reasoning models of similar size (median: 8).
How verbose is Qwen3.5 2B (Non-reasoning)?
When evaluated on the Intelligence Index, Qwen3.5 2B (Non-reasoning) generated 100M output tokens, which is at the higher end compared to other open weight non-reasoning models of similar size (median: 5.7M).
Is Qwen3.5 2B (Non-reasoning) a reasoning model?
No, Qwen3.5 2B (Non-reasoning) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
What input modalities does Qwen3.5 2B (Non-reasoning) support?
Qwen3.5 2B (Non-reasoning) supports text, image, and video input.
What output modalities does Qwen3.5 2B (Non-reasoning) support?
Qwen3.5 2B (Non-reasoning) supports text output.
Can Qwen3.5 2B (Non-reasoning) process images?
Yes, Qwen3.5 2B (Non-reasoning) supports image input and can analyze, describe, and answer questions about images.
Is Qwen3.5 2B (Non-reasoning) multimodal?
Yes, Qwen3.5 2B (Non-reasoning) is multimodal. It can process text, image, and video input and generate text output.
What is the context window of Qwen3.5 2B (Non-reasoning)?
Qwen3.5 2B (Non-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 2B (Non-reasoning) open source?
Yes, Qwen3.5 2B (Non-reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
How many parameters does Qwen3.5 2B (Non-reasoning) have?
Qwen3.5 2B (Non-reasoning) has 2.27 billion parameters.
What is the license for Qwen3.5 2B (Non-reasoning)?
Qwen3.5 2B (Non-reasoning) is released under the Apache 2.0 license. This license allows commercial use.
How does Qwen3.5 2B (Non-reasoning) perform on benchmarks?
Qwen3.5 2B (Non-reasoning) achieves a score of 15 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Is Qwen3.5 2B (Non-reasoning) available via API?
Qwen3.5 2B (Non-reasoning) is an open weights model that can be self-hosted.
