Roboflow

Qwen3.5 397B A17B vs SAM 3

Compare Qwen3.5 397B A17B and SAM 3 side-by-side.

Compare Qwen3.5 397B A17B vs SAM 3 live

Run the same image across every model that supports a task and compare their outputs side-by-side.

These models don't share enough common tasks for a side-by-side demo. See the comparison table below for their capabilities.

Models in this comparison

Meta

Qwen3.5 397B A17B vs SAM 3: Overview

Qwen3.5 397B A17B

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.

SAM 3

Released on November 19th, 2025, Segment Anything 3 (SAM 3) is a zero-shot image segmentation model that “detects, segments, and tracks objects in images and videos based on concept prompts.” This model was developed by Meta as the third model in the Segment Anything series.

Unlike its previous SAM models (Segment Anything and Segment Anything 2), you can provide SAM 3 with the prompt “shipping container” and it will generate precise segmentation masks for all shipping containers in an image. SAM 3 generates segmentation masks that correspond to the location of the objects found with a text prompt.

Qwen3.5 397B A17B vs SAM 3 Comparison Table

PropertyQwen3.5 397B A17BSAM 3
OrganizationQwenMeta
Categoryopenclosed
Modalitymultimodalmultimodal
Release DateFeb 2026Nov 2025
Context Window262K
Parameters397B
LicenseApache 2.0Proprietary
Pricing per 1M tokens
Input $/1M$0.385
Output $/1M$2.45
Vision Tasks
Object DetectionDemo
CaptioningDemo
Instance Segmentation
OCRDemo
Promptable Concept SegmentationDemo
Video Object Tracking
Vision Language
Visual Question AnsweringDemo
Zero Shot Segmentation
Model Features
Foundation Vision
LLMs with Vision Capabilities
Multimodal Vision
Zero-shot Detection
Vision Evalspass/fail results · 67 prompts
Score key:≥75%40–74%<40%
Visual Understanding
Overall Score
58.21%
Avg Response Time56.61s
Median input tokensincl. image tokens1.1K
Median output tokens54
Est. cost / taskon this benchmark$0.0006
Defect Detection
66.7%(10/15)
Document Understanding
77.8%(7/9)
Object Counting
20%(2/10)
Object Understanding
64.3%(9/14)
Spatial Understanding
57.9%(11/19)
OCR
Overall Score
68.56%
Avg Response Time7.45s
Median input tokensincl. image tokens122
Median output tokens20
Est. cost / taskon this benchmark$0.0001
Focused Scene OCR
57.6%(57/99)
Handwritten Math
80%(8/10)
License Plate Recognition
100%(30/30)
Text Recognition
70%(21/30)
VQA & Extraction
68.3%(41/60)

Output tokens (incl. reasoning) and est. cost / task are measured on this benchmark from a single low-temperature run, and shown only for models whose run covered at least 90% of prompts. Methodology