Muse Spark 1.3 vs Qwen3.5 9b
Compare Muse Spark 1.3 and Qwen3.5 9b side-by-side. See how these vision models stack up in Open Prompt, OCR, and Image Captioning.
Compare Muse Spark 1.3 vs Qwen3.5 9b 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
Muse Spark 1.3 vs Qwen3.5 9b on Vision Evals
Muse Spark 1.3 scores higher on all six Vision Evals tasks.
The widest gap is Reasoning, where Muse Spark 1.3 leads 73.3% to 50.3%.
Overall, Muse Spark 1.3 averages 79.8% (#10 of 52) against 66.1% (#33 of 52) for Qwen3.5 9b.
Qwen3.5 9b is cheaper ($0.0016 vs $0.0075 per sample), while Muse Spark 1.3 is faster (23.1s vs 31.3s per sample).
Muse Spark 1.3 vs Qwen3.5 9b Comparison Table
Evals updated September 3, 2026Pricing updated September 3, 2026
| Property | Muse Spark 1.3 | Qwen3.5 9b |
|---|---|---|
| Organization | Meta | Qwen |
| Category | closed | open |
| Modality | multimodal | multimodal |
| Release Date | Sep 2026 | Mar 2026 |
| Context Window | 1.0M | 262K |
| Parameters | 9B | |
| License | Proprietary | Apache 2.0 |
| Pricing per 1M tokens | ||
| Input $/1M | $1.25 | $0.100 |
| Output $/1M | $4.25 | $0.150 |
| 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 | 79.8% | 66.1% |
| Quantizationsself-hosted | ||
| Avg cost / sample | $0.0075 | $0.0016 |
| Avg speed / sample | 23.14s | 31.33s |
| By task | ||
| Object Detection (low) | 58.6% ±0.7, Mean of 3 runs, range 58.0 to 59.4 | 45.8% |
| Object Detection (high) | 56.6% ±2.4, Mean of 3 runs, range 54.5 to 59.3 | – |
| Counting (low) | 74.3% ±2.0, Mean of 3 runs, range 73.0 to 77.0 | 54.0% |
| Counting (high) | 75.7% ±3.4, Mean of 3 runs, range 73.0 to 79.7 | – |
| Identification (low) | 92.7% ±1.6, Mean of 3 runs, range 90.6 to 93.8 | 84.4% |
| Identification (high) | 86.5% ±1.6, Mean of 3 runs, range 84.4 to 87.5 | – |
| OCR (low) | 91.3% ±0.5, Mean of 3 runs, range 90.7 to 91.6 | 79.1% |
| OCR (high) | 86.9% ±4.1, Mean of 3 runs, range 82.2 to 90.4 | – |
| Data Extraction (low) | 88.7% ±1.5, Mean of 3 runs, range 86.6 to 89.7 | 82.7% |
| Data Extraction (high) | 87.6% ±0.0, Mean of 3 runs, range 87.6 to 87.6 | – |
| Reasoning (low) | 73.3% ±1.0, Mean of 3 runs, range 72.2 to 74.2 | 50.3% |
| Reasoning (high) | 73.1% ±1.0, Mean of 3 runs, range 72.2 to 74.2 | – |
Muse Spark 1.3 vs Qwen3.5 9b: Overview
Muse Spark 1.3 is a proprietary multimodal reasoning model from Meta Superintelligence Labs and the fourth Muse Spark release in five months, arriving on September 2, 2026. It takes text, images, video, and document files as input and returns text, and it operates over a context window of 1,048,576 tokens. Meta trains the model for long-horizon agentic work, so it carries accumulated context and prior tool results forward across many turns, reconciles messy or conflicting inputs, and asks for clarification when a task is underspecified. Visual inputs such as screenshots and video clips feed a reasoning loop that runs against a real execution environment rather than a scripted sequence of steps.
The model exposes graded reasoning effort settings. An xhigh configuration is generally available at launch, while a max reasoning configuration aimed at harder reasoning and agentic problems arrives after further safety testing. Artificial Analysis measures Muse Spark 1.3 (max) at 62 on its Intelligence Index and the xhigh configuration at 61, with agentic tool-use evaluations driving most of the gain over Muse Spark 1.2; max reaches 52% on Tau3-Bench Banking by spending more turns and reasoning tokens than xhigh. Prior Muse Spark versions emit bounding box coordinates, transcriptions, and structured field extractions from images on Roboflow Vision Evals.
Qwen3.5-9B is a 9-billion-parameter multimodal foundation model developed by Alibaba Cloud's Qwen team, released on March 2, 2026 as part of the Qwen3.5 model family. Designed for efficient multimodal reasoning and long-context language tasks, it notably outperforms the older Qwen3-30B, a model more than three times its size, on key benchmarks including GPQA Diamond, IFEval, and LongBench.
The model supports vision-language inputs through an early-fusion multimodal architecture built on a dense hybrid foundation of Gated Delta Networks and Gated Attention. It can also operate in a text-only mode by skipping the vision encoder during inference. It provides a 262,144-token context window (extensible to ~1M tokens via YaRN) and is released under the Apache License 2.0. Within the current AI landscape, Qwen3.5-9B offers a strong balance of capability and efficiency, making it well-suited for multimodal assistants, document analysis, long-context reasoning, and developer-deployed agentic systems.
Frequently Asked Questions
On Roboflow's Vision Evals, Muse Spark 1.3 performed better. It scores higher on all six vision tasks and averages 79.8% (#10 of 52) against 66.1% (#33 of 52) for Qwen3.5 9b. These scores measure vision capabilities only; either model may perform differently on work outside this benchmark's tasks.
Yes. On the Vision Evals Reasoning benchmark at low effort, Muse Spark 1.3 leads with 73.3% against 50.3%. This is the widest gap between the two models across the benchmark's tasks.
Qwen3.5 9b is cheaper to run. Across Roboflow's Vision Evals task mix it averaged $0.0016 per sample against $0.0075. Actual costs depend on your image sizes, prompts, and output length.
Muse Spark 1.3 is faster. Across Roboflow's Vision Evals it averaged 23.1s per inference against 31.3s. Latency varies with image size, prompt length, and provider load, so treat these as relative rather than guaranteed figures.
Yes. The comparison demo on this page runs both models on the same image side by side for open prompts and OCR in the free Roboflow Playground. You can try it instantly, and a free account unlocks unlimited runs.