Qwen3.5 397B A17B vs Qwen3.8 Max
Compare Qwen3.5 397B A17B and Qwen3.8 Max side-by-side. See how these vision models stack up in Image Captioning, OCR, and Open Prompt.
Compare Qwen3.5 397B A17B vs Qwen3.8 Max live
Run the same image across every model that supports a task and compare their outputs side-by-side.
Extract and compare text from images across multiple models.
Upload an image
Drag and drop an image here, or click to browse
Models in this comparison
Qwen3.5 397B A17B vs Qwen3.8 Max Comparison Table
Evals updated September 5, 2026Pricing updated September 13, 2026
| Property | Qwen3.5 397B A17B | Qwen3.8 Max |
|---|---|---|
| Organization | Qwen | Qwen |
| Category | open | closed |
| Modality | multimodal | multimodal |
| Release Date | Feb 2026 | Aug 2026 |
| Context Window | 262K | 984K |
| Parameters | 397B | 2.4T total, ~95B active |
| License | Apache 2.0 | Apache 2.0 |
| Pricing per 1M tokens | ||
| Input $/1M | $0.550 | |
| Output $/1M | $3.50 | |
| Vision Tasks | ||
| Captioning | Demo | Demo |
| Chart Question Answering | ||
| Classification | Demo | |
| Document Question Answering | ||
| Image Tagging | ||
| Multi-Label Classification | ||
| Object Detection | 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, pooled at low effort | ||
| Overall | Not evaluated | 83.9% |
| Avg cost / sample | – | $0.0074 |
| Avg speed / sample | – | 17.25s |
| By task | ||
| Object Detection (low) | – | 76.7% ±0.3, Mean of 3 runs, range 76.5 to 77.1 |
| Object Detection (high) | – | 78.4% ±0.4, Mean of 3 runs, range 78.1 to 78.9 |
| Counting (low) | – | 81.1% ±2.0, Mean of 3 runs, range 78.4 to 82.4 |
| Counting (high) | – | 81.1% ±0.0, Mean of 3 runs, range 81.1 to 81.1 |
| Identification (low) | – | 88.5% ±1.6, Mean of 3 runs, range 87.5 to 90.6 |
| Identification (high) | – | 89.6% ±1.6, Mean of 3 runs, range 87.5 to 90.6 |
| OCR (low) | – | 93.3% ±0.5, Mean of 3 runs, range 92.8 to 93.9 |
| OCR (high) | – | 91.3% ±0.5, Mean of 3 runs, range 90.7 to 91.7 |
| Data Extraction (low) | – | 87.6% ±0.0, Mean of 3 runs, range 87.6 to 87.6 |
| Data Extraction (high) | – | 89.3% ±1.0, Mean of 3 runs, range 88.7 to 90.7 |
| Reasoning (low) | – | 75.9% ±2.0, Mean of 3 runs, range 73.5 to 77.5 |
| Reasoning (high) | – | 80.3% ±2.0, Mean of 3 runs, range 78.2 to 82.1 |
Qwen3.5 397B A17B vs Qwen3.8 Max: Overview
Qwen3.5-397B-A17B is a 397B-parameter (17B active) open-weight multimodal model developed by Alibaba’s Qwen team, released on 2026-02-16 under Apache-2.0. It supports text and image inputs with text outputs, combining a sparse Mixture-of-Experts architecture with Gated Delta Networks for efficient scaling. The model provides native vision-language reasoning and a large ~262K token context window, extendable to ~1M tokens.
As the first open-weight release in the Qwen3.5 family, it positions itself as a high-capacity, long-context alternative in the large vision-language space, balancing scale and efficiency via sparse activation. It is designed for advanced reasoning, coding, agent workflows, and multimodal understanding tasks.
Qwen3.8 Max is the flagship tier of Alibaba's Qwen3.8 family, a sparse mixture-of-experts multimodal model with roughly 2.4 trillion total parameters of which about 95 billion activate per token, which keeps serving cost and latency well below what the total parameter count would imply. It builds on the architectural foundation established by Qwen3.5 and accepts text, images, video, and documents as input while producing text output. Reported context handling reaches close to one million tokens, with a maximum generation length of 131,072 tokens, so the model is aimed at long-horizon agentic work such as repository-scale coding, multi-step research, data analysis, and office document workflows.
For vision work the model performs image and video understanding, document and chart interpretation, text recognition inside images, and grounded visual question answering, and Alibaba reports gains concentrated in multimodal and agentic evaluation categories rather than general reasoning. Published figures include 86.6 on Terminal-Bench 2.1, 67.7 on SWE-bench Pro, 93.0 on PaperBench, 82.8 on IFBench, and 92.6 on GPQA Diamond. It is the first model in the Max tier of the Qwen line for which the team states weights will be released publicly, alongside a smaller Qwen3.8 27B checkpoint. No training or safety model card has been published.