Qwen3.6 Plus
4174°
Run this model
Offers / Ads
Qwen | 1,000,000 token context | $0.33/M input, $1.95/M output. Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers major gains in agentic coding, front-end development, and overall reasoning, with a significantly improved “vibe coding” experience. The model excels at complex tasks such as 3D scenes, games, and repository-level problem solving, achieving a 78.8 score on SWE-bench Verified. It represents a substantial leap in both pure-text and multimodal capabilities, performing at the level of leading state-of-the-art models.
Guides for this model
How to choose an AI model in October 2026: the closed source news, then the open weights worth downloading
Open weights vs open source vs API-only: what you are actually allowed to do
The 10 cheapest ChatGPT alternatives in 2026: free local models, free tiers and flat-rate plans
Captain's notes
Notes from 2026-10-13
Qwen 3.6 Plus is a closed-weights model from Qwen built on a hybrid linear-attention and sparse mixture-of-experts architecture, with a one-million-token context window. It targets agentic coding and complex reasoning, posting a 78.8 on SWE-bench Verified. At $0.33 per million input tokens it sits at a reasonable price for what it delivers, and it handles vision and video alongside text.
Known for
- 78.8 on SWE-bench Verified, strong for repository-level coding tasks
- One-million-token context window for very long documents or codebases
- Hybrid linear-attention plus sparse MoE architecture for efficient inference
- Vision and video inputs alongside text, not text-only
- Notably improved front-end and 'vibe coding' over the 3.5 series
Watch out for
- No open weights and no Hugging Face repository; you are API-only, full stop.
- Output at $1.95 per million tokens adds up fast on long agentic runs.
- Qwen has not published parameter count or licence terms for this model.
Prompts to try
Repo-level bug hunt
Here is a Python repository with a failing test. The test expects `calculate_discount` to return 0 for a negative input, but it raises a ValueError instead. Trace the call chain from the test through the service layer to the utility function, identify the root cause, and return a minimal diff that fixes it without changing the function's public interface.
3D scene code from scratch
Write a self-contained HTML file that renders an interactive 3D solar system using Three.js from a CDN. Include the Sun, Earth with a Moon, and Mars. Earth should orbit the Sun, the Moon should orbit Earth, and the user should be able to rotate and zoom the scene with the mouse. No external assets, no build step.
Multi-step agent plan
You are planning an autonomous coding agent. A user wants to migrate a Django 3.2 project to Django 5.1. List every discrete tool call the agent should make, in order, to audit breaking changes, update dependencies, patch deprecated code, run the test suite, and produce a migration report. Be specific about what each call checks or modifies.
Compare with
- Qwen3.8 FlashOpen-weights model1,000,000 token context · $0.15/M input, $0.47/M output
- Qwen3.8 27BOpen-weights model1,000,000 token context · $0.24/M input, $2.20/M output
- Qwen3.6 35B A3BOpen-weights model262,144 token context · $0.15/M input, $1.00/M output
- Qwen3.5-9BOpen-weights model262,144 token context · $0.10/M input, $0.15/M output
More text models from qwen
Questions people ask
- Can I run Qwen 3.6 Plus locally?
- No. Qwen has not released open weights for this model and there is no Hugging Face repository, so it is API-only.
- What does Qwen 3.6 Plus cost and how long is its context?
- Pricing is $0.33 per million input tokens and $1.95 per million output tokens, with a one-million-token context window.
- How does Qwen 3.6 Plus differ from the 3.5 series?
- Qwen says 3.6 Plus delivers major gains in agentic coding, front-end development, and reasoning over 3.5, with a substantially improved experience for iterative 'vibe coding' workflows.
Captain's verdictA serious agentic coding model at a fair input price, let down only by closed weights and output costs that climb on long runs.
Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.
Ranking badge
Updated Oct 22, 2026
Made this model? Show this badge on your page.
Paste it into your Hugging Face card or Civitai description.
How this score adds up
This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.
Glossary: the terms used here
- Heat score
- One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
- Floor
- The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
- Download-equivalents
- Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
- Log scale
- Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
- Likes
- Thumbs up and likes from every source, worth half a download each on the log scale.
- Adoption rate
- How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
- Measured and estimated
- Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
- Seeder
- Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
- AI Horde
- A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
- Generation sites
- Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
- OpenRouter tokens
- A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
- Full model (checkpoint)
- The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
- LoRA and embedding
- Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
- Family and weights
- The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
- Age
- Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
- Family boost
- A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
- Stand-in score
- A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
- New! (grace period)
- A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
- Trend
- How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
- Typical model
- The middle of the catalog: half the models with a figure grew faster over the period, half slower.
Qwen3.6 Plus is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.
Browse by Model Family
Text / LLM Models
434
Anima Models
528
Chroma Models
19
Fibo Models
2
Flux Models
1,496
Flux 2 / Klein Models
1,239
Flux 3 Models
3
Moss Models
3
Iris Models
1
MiniMax H3 Models
364
Hunyuan Models
204
Ideogram Models
20
Krea2 Models
717
Qwen Models
20
Qwen2 Models
47
Ltx2 Models
153