# Qwen3.5 Small

Qwen3.5 Small is an AI model released by Qwen on Mar 2 2026. It has 0.8B/2B/4B/9B parameters, a 256k context window and open weight. Tracked results include 81.7% on GPQA Diamond, 65.6% on LiveCodeBench and 78.4% on MMMU.

## Facts

| Field | Value |
| --- | --- |
| Model | Qwen3.5 Small |
| Developer | Qwen |
| Release date | Monday, Mar 2 2026 |
| Licensing | Open Weight |
| Parameters | 0.8B/2B/4B/9B |
| Context window | 256k |

## Tracked benchmark scores

| Benchmark | Score | Source | What it measures |
| --- | --- | --- | --- |
| LiveCodeBench | 65.6% | Lab | Coding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. |
| IFEval | 91.5% | Lab | following verifiable instructions in generated responses |
| GPQA Diamond | 81.7% | Lab | Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. |
| IFBench | 64.5% | Lab | Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. |
| MMLU-Pro | 82.5% | Lab | accuracy on the ten-option MMLU-Pro benchmark |
| OSWorld-Verified | 41.8% | Lab | Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. |
| CharXiv Reasoning | 73% | Lab | Can the AI read and reason about complex charts and figures, not just text? Higher is better. |
| MMMU-Pro | 70.1% | Lab | A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. |
| MMMU | 78.4% | Lab | Tests the AI on understanding images and text together across many college subjects. Higher is better. |

## About Qwen3.5 Small

The Qwen3.5 Small release shipped on March 2, 2026 with 0.8B, 2B, 4B and 9B open-weight models. It completed the Qwen3.5 size lineup and offered thinking and visual understanding at sizes intended for local and edge deployments.

The benchmark scores on this page come from the 9B checkpoint, which scored 81.7 on GPQA Diamond and 65.6 on LiveCodeBench v6. The smaller checkpoints offered different memory and performance trade-offs under the same family name.

## Questions and answers

### When was Qwen3.5 Small released?

Qwen3.5 Small was released by Qwen on Monday, Mar 2 2026.

### Who made Qwen3.5 Small?

Qwen3.5 Small was built by Qwen. Alibaba's AI lab, building the Qwen family. The most prolific publisher of open-weight models of any major lab, alongside a closed Max and Plus tier sold through Alibaba Cloud.

### What benchmark scores did Qwen3.5 Small get?

Qwen3.5 Small reports 9 tracked benchmark scores — LiveCodeBench: 65.6%; IFEval: 91.5%; GPQA Diamond: 81.7%; IFBench: 64.5%; MMLU-Pro: 82.5%; OSWorld-Verified: 41.8%; CharXiv Reasoning: 73%; MMMU-Pro: 70.1%; MMMU: 78.4%. Tracked scores may come from lab reports or independent benchmarks; source details accompany the benchmark data.

### What is the context window of Qwen3.5 Small?

Qwen3.5 Small has a context window of 256k. Providers may specify separate input and output token limits.

### How many parameters does Qwen3.5 Small have?

Qwen3.5 Small is reported at 0.8B/2B/4B/9B parameters.

### Is Qwen3.5 Small open source?

Partly. Qwen3.5 Small is an open-weight model: the trained weights are free to download and run locally or on your own infrastructure, but the training data and code are not fully released and the license may restrict some commercial uses. It is not open source in the strict sense.

### What came before and after Qwen3.5 Small?

Qwen's previous tracked release was Qwen3.5 Medium on Feb 24 2026, 6 days earlier. It was followed by Qwen3.6-Plus on Apr 2 2026.


---

Canonical page: https://aireleasetracker.com/model/qwen/qwen3.5-small
Site index: https://aireleasetracker.com/llms.txt
Source: AI Release Tracker (https://aireleasetracker.com). Most benchmark scores come from lab launch material; gathered results identify the leaderboard that published them.
