Gemma 4 31B vs Qwen3.5-27B
Compare Gemma 4 31B and Qwen3.5-27B side-by-side. See how these vision models stack up in Image Captioning, OCR, Open Prompt, Object Detection, and Classification.
Compare Gemma 4 31B vs Qwen3.5-27B 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
Models in this comparison
Gemma 4 31B vs Qwen3.5-27B on Vision Evals
Qwen3.5-27B scores higher on 5 of the six Vision Evals tasks.
The widest gap is Counting, where Qwen3.5-27B leads 67.6% to 51.4%.
Overall, Gemma 4 31B averages 67.0% (#34 of 59) against 70.8% (#25 of 59) for Qwen3.5-27B.
Gemma 4 31B is both cheaper ($0.0015 vs $0.0043 per sample) and faster (34.4s vs 80.4s per sample).
Gemma 4 31B vs Qwen3.5-27B Comparison Table
Evals updated September 22, 2026Pricing updated September 24, 2026
| Property | Gemma 4 31B | Qwen3.5-27B |
|---|---|---|
| Organization | Qwen | |
| Category | open | open |
| Modality | multimodal | multimodal |
| Release Date | Apr 2026 | Feb 2026 |
| Context Window | 256K | 262K |
| Parameters | 31B | 27B |
| License | Apache 2.0 | Apache 2.0 |
| Pricing per 1M tokens | ||
| Input $/1M | $0.090 | $0.195 |
| Output $/1M | $0.340 | $1.56 |
| Vision Tasks | ||
| Captioning | Demo | Demo |
| Chart Question Answering | ||
| Classification | Demo | Demo |
| Document Question Answering | ||
| Image Tagging | ||
| Multi-Label Classification | ||
| Object Detection | Demo | Demo |
| OCR | Demo | Demo |
| Vision Language | ||
| Visual Question Answering | Demo | Demo |
| Model Features | ||
| Foundation Vision | ||
| LLMs with Vision Capabilities | ||
| Multimodal Vision | ||
Vision Evalsground-truth scores across 6 vision tasks | ||
| Overall | 67.0% | 70.8% |
| Quantizationsself-hosted | ||
| Avg cost / sample | $0.0015 | $0.0043 |
| Avg speed / sample | 34.36s | 80.37s |
| By task | ||
| Object Detection | 47.5% ±0.6, Mean of 3 runs, range 46.8 to 48.0 | 50.5% ±3.5, Mean of 3 runs, range 46.1 to 53.0 |
| Counting | 51.4% ±2.7, Mean of 3 runs, range 48.6 to 54.0 | 67.6% ±1.4, Mean of 3 runs, range 66.2 to 68.9 |
| Identification | 79.2% ±1.6, Mean of 3 runs, range 78.1 to 81.3 | 80.2% ±4.7, Mean of 3 runs, range 75.0 to 84.4 |
| OCR | 90.8% ±0.6, Mean of 3 runs, range 90.2 to 91.5 | 84.7% ±3.3, Mean of 3 runs, range 80.8 to 87.3 |
| Data Extraction | 80.4% ±1.0, Mean of 3 runs, range 79.4 to 81.4 | 83.8% ±1.5, Mean of 3 runs, range 82.5 to 85.6 |
| Reasoning | 52.8% ±1.3, Mean of 3 runs, range 51.7 to 54.3 | 58.1% ±2.3, Mean of 3 runs, range 55.6 to 60.3 |
Gemma 4 31B vs Qwen3.5-27B: Overview
Gemma 4 31B is the largest dense model in Google's Gemma 4 family, built from the same research as Gemini 3 and released as open weights under the Apache 2.0 license. It supports a 256K token context window with text and image input, configurable thinking mode for step-by-step reasoning, and multilingual support across 140+ languages. The unquantized model fits on a single 80GB GPU.
For vision tasks, Gemma 4 31B supports image understanding with variable aspect ratios and resolutions, and can output structured bounding boxes for UI element detection, making it useful for document parsing and UI understanding. Compared to Gemma 3, it delivers stronger reasoning and multimodal performance. It is part of a four-size family alongside the 26B A4B MoE variant and two on-device models (E2B, E4B), with the 31B dense variant optimized for output quality and fine-tuning over inference speed.
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. This design provides the highest instruction-following and coding accuracy in its class, with a notable IFEval score of 95.0. 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. This unified approach allows the model to excel in technical analysis and software engineering, matching GPT-5-mini with a 72.4% score on SWE-bench Verified. 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.