# Qwen3.5 Medium

Qwen3.5 Medium is an AI model released by Qwen on Feb 24 2026. It has 27B/35B/122B parameters, a 256k context window and open weight. Tracked results include 86.6% on GPQA Diamond, 72% on SWE-Bench Verified and 78.9% on LiveCodeBench.

## Facts

| Field | Value |
| --- | --- |
| Model | Qwen3.5 Medium |
| Developer | Qwen |
| Release date | Tuesday, Feb 24 2026 |
| Licensing | Open Weight |
| Parameters | 27B/35B/122B |
| Context window | 256k |

## Tracked benchmark scores

| Benchmark | Score | Source | What it measures |
| --- | --- | --- | --- |
| SWE-Bench Verified | 72% | Lab | Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. |
| LiveCodeBench | 78.9% | 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. |
| Terminal-Bench 2.0 | 49.4% | Lab | Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? (Version 2.0 of the test.) Higher is better. |
| IFEval | 93.4% | Lab | following verifiable instructions in generated responses |
| BrowseComp | 63.8% | Lab | Can the AI browse the web and track down hard-to-find answers? Higher is better. |
| Humanity's Last Exam (no tools) | 25.3% | Lab | Humanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better. |
| Humanity's Last Exam (with tools) | 47.5% | Lab | Humanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better. |
| GPQA Diamond | 86.6% | Lab | Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. |
| IFBench | 76.1% | Lab | Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. |
| MMLU-Pro | 86.7% | Lab | accuracy on the ten-option MMLU-Pro benchmark |
| OSWorld-Verified | 58% | 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 | 77.2% | Lab | Can the AI read and reason about complex charts and figures, not just text? Higher is better. |
| MMMU-Pro | 76.9% | Lab | A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. |
| MMMU | 83.9% | Lab | Tests the AI on understanding images and text together across many college subjects. Higher is better. |

## About Qwen3.5 Medium

The open-weight Qwen3.5 Medium release grouped the 27B dense and 35B-A3B and 122B-A10B mixture-of-experts checkpoints. It brought the February 2026 flagship's text and vision functions to three smaller deployment sizes.

The benchmark scores on this page come from the 122B-A10B checkpoint, which scored 86.6 on GPQA Diamond and 72.0 on SWE-bench Verified. Qwen documented Qwen3.5-Flash as a hosted counterpart to the 35B-A3B checkpoint, with a one-million-token default context and built-in tools.

## Questions and answers

### When was Qwen3.5 Medium released?

Qwen3.5 Medium was released by Qwen on Tuesday, Feb 24 2026.

### Who made Qwen3.5 Medium?

Qwen3.5 Medium 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 Medium get?

Qwen3.5 Medium reports 14 tracked benchmark scores — SWE-Bench Verified: 72%; LiveCodeBench: 78.9%; Terminal-Bench 2.0: 49.4%; IFEval: 93.4%; BrowseComp: 63.8%; Humanity's Last Exam (no tools): 25.3%; Humanity's Last Exam (with tools): 47.5%; GPQA Diamond: 86.6%; IFBench: 76.1%; MMLU-Pro: 86.7%; OSWorld-Verified: 58%; CharXiv Reasoning: 77.2%; MMMU-Pro: 76.9%; MMMU: 83.9%. Tracked scores may come from lab reports or independent benchmarks; source details accompany the benchmark data.

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

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

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

Qwen3.5 Medium is reported at 27B/35B/122B parameters.

### Is Qwen3.5 Medium open source?

Partly. Qwen3.5 Medium 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 Medium?

Qwen's previous tracked release was Qwen3.5-Plus on Feb 16 2026, 8 days earlier. It was followed by Qwen3.5 Small on Mar 2 2026.


---

Canonical page: https://aireleasetracker.com/model/qwen/qwen3.5-medium
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.
