Qwen3.5-27B vs Qwen3.6 35B A3B
Qwen3.6 35B A3B and Qwen3.5-27B score 64.8% vs 64.1% averaged across four Vision Evals tasks (#33 and #35 of 68 models), so they are effectively tied.
- The task wins split 2-2, and the widest gap is object detection, where Qwen3.6 35B A3B leads 57.0% vs 50.5%.
- Qwen3.6 35B A3B is about a quarter of the cost: $0.0012 vs $0.0043 overall average cost per sample.
- Qwen3.6 35B A3B is faster: 27.1s vs 80.4s per sample.
Roboflow Vision Evals. Full breakdown below.
Compare Qwen3.5-27B vs Qwen3.6 35B A3B live
Run the same image across every model that supports a task and compare their outputs side-by-side.
Detect and compare bounding boxes across models on the same image.
Upload an image
Drag and drop an image here, or click to browse
Qwen3.5-27B vs Qwen3.6 35B A3B on Vision Evals
Roboflow Vision Evals. Full breakdown below.
Qwen3.5-27B vs Qwen3.6 35B A3B Comparison Table
Evals updated November 10, 2026Pricing updated November 10, 2026
| Property | Qwen3.5-27B | Qwen3.6 35B A3B |
|---|---|---|
| Organization | Qwen | Qwen |
| Category | open | open |
| Modality | multimodal | multimodal |
| Release Date | Feb 2026 | Apr 2026 |
| Context Window | 262K | 262K |
| Parameters | 27B | 35B total, 3B active |
| License | Apache 2.0 | Apache 2.0 |
| Commercial use | free for commercial use | free for commercial use |
| Pricing per 1M tokens | ||
| Input $/1M | $0.260 | $0.100 |
| Output $/1M | $2.60 | $0.900 |
| Vision Tasks | ||
| Phrase Grounding | Not listed | Supported |
| Video Classification | Not listed | Supported |
| Model Features | ||
Both support 3 more features | ||
Vision Evalsground-truth scores across 5 vision tasks | ||
| Overall | 64.1%* | 64.8%* |
| Quantizationsself-hosted | ||
| Avg cost / sample | $0.0043 | $0.0012 |
| Avg speed / sample | 80.37s | 27.10s |
| By task | ||
| Object Detection | 50.5% ±3.5, Mean of 3 runs, range 46.1 to 53.0 | 57.0% ±1.3, Mean of 3 runs, range 56.1 to 58.7 |
| Counting | 67.6% ±1.4, Mean of 3 runs, range 66.2 to 68.9 | 65.3% ±2.7, Mean of 3 runs, range 62.2 to 67.6 |
| Identification | 80.2% ±4.7, Mean of 3 runs, range 75.0 to 84.4 | 82.3% ±6.3, Mean of 3 runs, range 75.0 to 87.5 |
| OCR | – | – |
| by category | ||
| Reasoning | 58.1% ±2.3, Mean of 3 runs, range 55.6 to 60.3 | 54.8% ±1.3, Mean of 3 runs, range 53.0 to 55.6 |
Qwen3.5-27B vs Qwen3.6 35B A3B: Overview
Qwen3.5-27B is a multimodal dense hybrid model developed by Alibaba Cloud’s Qwen team and released in February 2026 as a high-precision entry in the Qwen3.5 "Medium" series. Unlike its Mixture-of-Experts (MoE) siblings, the 27B model utilizes a dense architecture combining Gated Delta Networks with a feed-forward structure, activating its full parameter suite for every inference to maximize reliability. The model features a native 262K-token context window, extensible to 1M tokens via YaRN (RoPE scaling), and is released under the Apache-2.0 license.
Optimized for agentic workflows, Qwen3.5-27B employs an early-fusion architecture that treats visual and textual data as a unified stream for deep cross-modal reasoning. While the larger MoE variants in the family lead in raw knowledge benchmarks, the 27B model offers a stable and high-density alternative for structured data extraction and spatial perception, contributing to the Qwen3.5 family’s generational leap in OCR accuracy over the previous Qwen3-VL series.
Qwen3.6-35B-A3B is a sparse Mixture-of-Experts (MoE) multimodal language model developed by the Qwen team at Alibaba Group. It carries 35 billion total parameters but activates only approximately 3 billion per forward pass via a learned routing mechanism, giving it the representational capacity of a large dense model at a fraction of the inference compute. The model is natively multimodal, processing images, documents, and video alongside text as a core architectural capability rather than an add-on. It supports a native context window of 262,144 tokens, extensible up to 1,010,000 tokens via YaRN. A key design feature is the unified thinking/non-thinking mode framework: users can switch between deliberate chain-of-thought reasoning and fast direct responses within a single model, and a "thinking preservation" option retains reasoning context across multi-turn agentic workflows to reduce redundant computation.
The model is specifically optimized for agentic coding tasks, including repository-level reasoning, frontend workflow generation, multi-step tool use, and MCP (Model Context Protocol) integration. For vision-language tasks it achieves 92.0 on RefCOCO, 89.9 on OmniDocBench 1.5, and 83.7 on VideoMMMU. The model also supports Multi-Token Prediction (MTP) for speculative decoding. All Qwen3.6 open-weight models are released under the Apache 2.0 license.