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.
Drag and drop an image here, or click to browse
Model settings
Thinking level
Max output tokens
Default 65,536 · max 65,536
Sign in to adjust thinking and output length per run.
Results appear here. Add an image or pick an example to run Muse Spark 1.3.
—
Usage
Past 30 DaysVision Evals is Roboflow's ground-truth benchmark: every model runs the same real-world samples across six vision tasks, and answers are scored against ground truth.
Evals updated September 3, 2026Pricing updated September 3, 2026
Muse Spark 1.3 averages 79.8% across the six Vision Evals tasks, ranking #10 of 52 models overall.
Its weakest relative showing is Object Detection, ranking #17 of 52 at 58.6%.
At $0.0075 per sample it is the 41st cheapest of the 52 benchmarked models, and its average inference time of 23.1s per sample makes it the 40th fastest.
Field medians: Object Detection 54.1%, Counting 56.8%, Identification 84.4%, OCR 88.1%, Data Extraction 84.5%, Reasoning 53.6%.
| Task | Score | Field (0 to 100) | Rank | Cost / sample | Speed |
|---|---|---|---|---|---|
| Object Detection (low) | 58.6% ±0.7, Mean of 3 runs, range 58.0 to 59.4 | #17 of 52 | $0.011 | 25.79s | |
| Object Detection (high) | 56.6% ±2.4, Mean of 3 runs, range 54.5 to 59.3 | #10 of 10 | $0.017 | 39.05s | |
| Counting (low) | 74.3% ±2.0, Mean of 3 runs, range 73.0 to 77.0 | #8 of 52 | $0.0049 | 20.06s | |
| Counting (high) | 75.7% ±3.4, Mean of 3 runs, range 73.0 to 79.7 | #7 of 10 | $0.0094 | 29.52s | |
| Identification (low) | 92.7% ±1.6, Mean of 3 runs, range 90.6 to 93.8 | #10 of 52 | $0.0036 | 14.53s | |
| Identification (high) | 86.5% ±1.6, Mean of 3 runs, range 84.4 to 87.5 | #9 of 10 | $0.0063 | 21.06s | |
| OCR (low) | 91.3% ±0.5, Mean of 3 runs, range 90.7 to 91.6 | #14 of 52 | $0.0083 | 32.47s | |
| OCR (high) | 86.9% ±4.1, Mean of 3 runs, range 82.2 to 90.4 | #10 of 10 | $0.015 | 57.96s | |
| Data Extraction (low) | 88.7% ±1.5, Mean of 3 runs, range 86.6 to 89.7 | #13 of 52 | $0.0031 | 14.60s | |
| Data Extraction (high) | 87.6% ±0.0, Mean of 3 runs, range 87.6 to 87.6 | #9 of 10 | $0.0044 | 16.84s | |
| Reasoning (low) | 73.3% ±1.0, Mean of 3 runs, range 72.2 to 74.2 | #8 of 52 | $0.0064 | 25.27s | |
| Reasoning (high) | 73.1% ±1.0, Mean of 3 runs, range 72.2 to 74.2 | #12 of 37 | $0.012 | 44.44s |
Overall benchmark score against estimated cost per sample, on a log scale. Upper-left is the sweet spot: high quality at low cost.
51 models on the current benchmark · scores and efficiency pooled across all six tasks at low effort · Muse Spark 1.3 highlighted
Muse Spark 1.3 scores are the mean of 3 runs per task at both low and high effort · Methodology
View all Vision Evals →Muse Spark 1.3 costs $1.25 per 1M input tokens and $4.25 per 1M output tokens.
Pricing updated Sep 3, 2026
Muse Spark 1.3 is proprietary: the weights are not distributed, and the Muse Spark 1.3 license is the vendor's commercial terms of service that you accept when you call the API.
Vendor terms govern data retention, whether your inputs can be trained on, rate limits, and regional availability, and they can change with notice. Review them if you handle regulated or customer data.
Proprietary terms are set by the vendor rather than negotiated per project, and no open-source obligation attaches to your code. If you would rather deploy a model whose commercial license is included in your plan — on Roboflow Managed Cloud or a Self-Hosted Inference Server — Roboflow's licensing page lists the supported alternatives to Muse Spark 1.3.
Do not hesitate to reach out with questions for your commercial project — our team will help you start solving business problems on the first call. See Roboflow commercial licensing for the models included in each plan.
Talk to salesThis model is proprietary. The author retains all rights, and use of the model is governed by their specific terms of service or license agreement.
Commercial use depends on the terms set by the model author. Most proprietary commercial models require a paid subscription, API key, or per-call billing. Check the provider’s pricing and terms-of-service for details.
License information is provided as a guide and is not legal advice.
Yes. Muse Spark 1.3 accepts image input and handles OCR, data extraction, object counting, identification, visual reasoning, and object detection. On Roboflow's Vision Evals its strongest task is Counting at 74.3% (#8 of 52 at low effort). You can test it on your own image in the demo above.
Yes, and it is one of the model's strongest vision skills: its transcriptions match the ground truth 91.3% on average (#14 of 52 at low effort) on Vision Evals OCR. Pulling specific fields out of documents (data extraction) scores 88.7%.
It's serviceable. On Vision Evals, Muse Spark 1.3 scores 58.7% mAP@50 on object detection (#17 of 52 at low effort) and 74.3% judge-graded accuracy on object counting.
On our benchmark's task mix, Muse Spark 1.3 averages $0.0075 per sample at $1.25 per 1M input and $4.25 per 1M output tokens (#41 of 52 on cost), with an average speed of 23.1s per sample across the benchmark. Actual cost depends on your images and prompts.
On the overall Vision Evals ranking, Muse Spark 1.3 sits #10 of 52 at 79.8%, just behind Muse Spark 1.2 (80.5%) and just ahead of Claude Fable 5 (78.7%). See the full side-by-side: Muse Spark 1.3 vs Muse Spark 1.2.