Roboflow
Qwen

Qwen: Qwen3.5 122B A10B

Qwen3.5 122B A10B Overview

Qwen3.5-122B-A10B is a high-capacity multimodal Mixture-of-Experts (MoE) model developed by Alibaba’s Qwen team as part of the Qwen3.5 model family. The architecture contains 122 billion total parameters while activating roughly 10 billion per token through sparse expert routing, allowing the model to balance large-scale reasoning ability with relatively efficient inference compared to dense models of similar size.

The model is designed to process both text and visual inputs within a unified multimodal framework, enabling tasks that require reasoning across images, documents, charts, and natural language. This makes it suitable for applications such as document understanding, diagram interpretation, and complex visual question answering.

Qwen3.5-122B-A10B supports a native context window of approximately 256,000 tokens, which can be extended further through techniques such as YaRN scaling to support very long-context workloads. Released under the Apache 2.0 license, it builds on earlier Qwen multimodal systems and provides developers with an open-weight model capable of handling demanding multimodal reasoning and analysis tasks.

Qwen3.5 122B A10B Interactive Demo

Qwen3.5 122B A10B Details & Performance

Details

Resources

Vision Tasks

Vision LanguageObject DetectionOCRVisual Question AnsweringCaptioning

Features

LLMs with Vision CapabilitiesMultimodal Vision

Usage

Past 30 Days

Performance

Avg. Latency

Arena Rankings

Qwen3.5 122B A10B Vision Evals

Qwen3.5 122B A10B has not yet been evaluated on the current benchmark. The results below are from the legacy version of Vision Evals, our previous benchmark. See the current Vision Evals

Visual Understanding

77 models · 67 tasks
HighestLowest
This model#9 of 7776.12% pass rate · better than 86%
Score76.12%pass rate across 67 tasks
Speed1.77savg response per task
Cost$0.0003 / task$0.260 in · $2.08 out / 1M
Tokens1.2K / task1.2K in · 7 out
Score key:≥75%40–74%<40%
CategoryPassedScore
Object Understanding13 / 14
92.9%
Defect Detection13 / 15
86.7%
Document Understanding7 / 9
77.8%
Spatial Understanding14 / 19
73.7%
Object Counting4 / 10
40%

Scores based on a single evaluation run · Methodology

View all legacy Vision Evals results →

Qwen3.5 122B A10B Pricing

Qwen3.5 122B A10B costs $0.260 per 1M input tokens and $2.08 per 1M output tokens.

Input$0.260 / 1M tokens
Output$2.08 / 1M tokens

Pricing updated Jul 21, 2026

Price vs. performance

Estimated cost per task vs. Visual Understanding score, for this model and others ranked near it. Upper-left is the sweet spot (high quality, low cost). Based on Vision Evals (legacy) results.

11 of 11 models plotted

ModelScoreMedian tokensEst. cost / taskCompare
GoogleGemini 3.5 Flash79.1%1.4K$0.0043Compare
AnthropicClaude Fable 579.1%2.9K$0.041Compare
OpenAIGPT-5.4 Mini77.6%1.9K$0.0015Compare
OpenAIGPT-5.477.6%1.7K$0.0052Compare
OpenAIGPT-5.577.6%1.7K$0.011Compare
QwenQwen3.5 122B A10B(this model)76.1%1.2K$0.0003
OpenAIGPT-5.6 Terra76.1%1.5K$0.0041Compare
OpenAIGPT-5.6 Sol76.1%1.5K$0.0073Compare
GoogleGemini 3.1 Pro75.8%1.1K$0.0024Compare
GoogleGemini 3 Flash74.6%1.4K$0.0014Compare
OpenAIGPT-5 Mini73.1%1.8K$0.0006Compare

Alternatives to Qwen3.5 122B A10B

Other models worth comparing for similar use cases.

Qwen
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.
Qwen
Qwen3 VL 235B A22B Instruct
Qwen3 VL 235B A22B Instruct is a flagship multimodal vision-language model developed by Qwen (Alibaba Cloud), designed for instruction-following tasks that combine advanced text generation with visual understanding. It serves as a high-end open-weight model for developers and researchers building multimodal AI systems that require strong reasoning, perception, and long-context capabilities.The model supports interleaved text and image inputs, very long context windows (up to roughly 256K tokens), and efficient inference through a mixture-of-experts architecture with about 22B active parameters out of 235B total. In today’s landscape, it competes with top-tier proprietary vision-language models while offering the advantages of open weights and flexible deployment. Typical applications include multimodal assistants, document and image analysis, visual reasoning, and large-context instruction-based workflows.
Meta
Llama 4 Maverick
Llama 4 Maverick, introduced on April 5, 2025, is one of the first models in Meta’s Llama 4 family, designed as a natively multimodal model supporting text + image inputs with text outputs. It employs a Mixture-of-Experts (MoE) architecture with 128 experts, activating ~17B parameters per token out of a pool of ~400B total parameters. This design improves scalability, efficiency, and reasoning capacity. Maverick has a 1M-token context window, enabling it to handle large documents, extended conversations, and multimodal reasoning. Its knowledge cutoff is August 2024.The model is released under the Llama 4 Community License and comes in both base and instruction-tuned (“Instruct”) versions. Maverick is widely deployed via Hugging Face, Google Vertex AI, Amazon Bedrock, and Oracle Cloud, making it one of the most accessible large open-weight models. However, it outputs text only (no image/audio generation) and, while input capacity is huge, output limits are typically much smaller. The MoE design also raises hardware demands, as maintaining 128 experts requires significant compute resources, and Meta’s license introduces restrictions around commercial-scale use.
Google
Gemini 3.1 Pro
Gemini 3.1 Pro is a proprietary multimodal model from Google’s Gemini 3 series, released in early 2026 and designed for advanced reasoning across large multimodal datasets. It accepts text, images, audio, video, and documents, supporting up to a 1-million-token input context with up to 64k output tokens. Compared with Gemini 3 Pro, it improves long-context synthesis and multi-step reasoning, enabling more reliable analysis of large documents, datasets, and software codebases.The model also advances visual understanding and grounding, allowing it to interpret UI screenshots, diagrams, and real-world scenes while referencing specific regions within images or video. These capabilities make Gemini 3.1 Pro well suited for multimodal workflows involving document processing, interface analysis, robotics research, and complex visual reasoning.
Anthropic
Claude Opus 4.6
Claude Opus 4.6 is the flagship large language model from Anthropic, released on 2026-02-05 for advanced reasoning, complex coding, and enterprise agent workflows. It supports text and image inputs via API, offers a 200K-token standard context window with a 1M-token beta option, and enables outputs up to 128K tokens, with adaptive reasoning and context compaction for sustained tasks.As of 2026-02-17, Anthropic also released Claude Sonnet 4.6, extending the 1M-token context window to a broader tier. Opus remains positioned for maximum depth and benchmark performance, while Sonnet 4.6 brings long-context capability to more cost- and latency-sensitive production use cases.
MoonshotAI
Kimi K2.5
Kimi K2.5 is a frontier-scale multimodal AI model developed by Moonshot AI and released on January 27, 2026. As a significant advancement within the Kimi K2 family, it utilizes a sparse Mixture-of-Experts (MoE) architecture with 1 trillion total parameters (32 billion active per inference) and a massive 256K-token context window. The model features native multimodal integration via a 400M-parameter MoonViT encoder, allowing it to process text, images, and video frames simultaneously. Built for both speed and depth, it offers "Instant" and "Thinking" modes, the latter of which excels at expert-level reasoning, scoring 50.2% on the Humanity’s Last Exam (HLE) benchmark when equipped with tools.The model is released under a Modified MIT License, which remains open-weight but requires attribution for high-revenue commercial entities. It introduces an "Agent Swarm" paradigm capable of coordinating up to 100 specialized sub-agents for parallel workflows, significantly reducing latency in complex research tasks. For vision tasks, Kimi K2.5 demonstrates strong autonomous visual debugging capabilities, where it can inspect its own generated UI outputs against visual specifications to iteratively refine frontend code. This makes it a powerful choice for developers testing automated UI reconstruction, high-fidelity OCR document processing, and multi-step agentic research grounded in complex visual data.

Qwen3.5 122B A10B License

Apache 2.0

License terms and commercial-use guidance for Qwen3.5 122B A10B.

This model is released under the Apache License 2.0, a permissive open-source license that allows commercial use, modification, distribution, and patent use.

Read the full Apache 2.0 license ↗

Yes. Under the terms of the Apache 2.0 license, you can freely use this model for commercial purposes, including in proprietary products. You must retain the copyright notice and disclaimers when redistributing.

License information is provided as a guide and is not legal advice.

Frequently Asked Questions About Qwen3.5 122B A10B Vision

Yes. Qwen3.5 122B A10B accepts image input, and on Roboflow's previous vision benchmark it passed 76.1% of visual understanding tasks (#9 of 77). You can test it on your own image in the demo above.

Qwen3.5 122B A10B has not yet been evaluated on Roboflow's current Vision Evals. The results on this page are from the previous benchmark.

Yes. The demo on this page runs Qwen3.5 122B A10B in the free Roboflow Playground: upload an image and see results in seconds. A free account unlocks unlimited runs.