Not available to run yet
Muse Wonder is on the Vision Evals leaderboard. Running it in the Playground is not available yet. View evals
Muse Wonder is a proprietary multimodal reasoning model from Meta, released on October 12, 2026 as the first step past the Muse Spark line on Meta's scaling ladder. It launched together with Muse Wonder Full, a larger configuration that is available only through Muse Code subscription plans, while Muse Wonder itself is served through the Meta Model API under the identifier muse-wonder-1.0. The model accepts text, images, video, audio, and PDF documents as input and returns text, with a context window of 1,048,576 tokens and graded reasoning effort settings. Meta trained both models at its Prometheus data center on larger base models than Muse Spark 1.3, and attributes their gains on unfamiliar tasks to post-training that transfers more effectively from a stronger base.
Meta positions Muse Wonder for long-running personal and professional agents: it plans multi-step work, delegates to sub-agents, calls tools in parallel, recovers from errors, and operates browsers and desktop or mobile applications. Two training objectives shape this behaviour. Active Memory carries goals, constraints, and earlier decisions across conversations and retrieves the details relevant to the current step, and Active Focus keeps the model trying alternative approaches when a task gets difficult while asking for clarification before important actions. Visual inputs such as screenshots, charts, and video feed the same reasoning loop, and the model emits bounding box coordinates for grounding queries. Meta's model card lists visual and spatial reasoning, especially 3D tasks, as a known limitation and recommends validating performance for applications that depend on precise spatial understanding.
—
Usage
Past 30 DaysNot available
Not in Playground
Vision Evals is Roboflow's ground-truth benchmark: every model runs the same real-world samples across five vision tasks, and answers are scored against ground truth.
Evals updated October 13, 2026Pricing updated October 13, 2026
Muse Wonder averages 78.8% across the five Vision Evals tasks, ranking #8 of 62 models overall.
It places in the top three for Reasoning.
Its weakest relative showing is Object Detection, ranking #15 of 62 at 65.1%.
At $0.034 per sample it is the 60th cheapest of the 62 benchmarked models, and its average inference time of 11.7s per sample makes it the 38th fastest.
Field medians: Object Detection 54.3%, Counting 63.1%, Identification 84.4%, OCR 62.5%, Reasoning 57.6%.
| Task | Score | Field (0 to 100) | Rank | Cost / sample | Speed |
|---|---|---|---|---|---|
| Object Detection (low) | 65.1% ±0.8, Mean of 3 runs, range 64.5 to 66.0 | #15 of 62 | $0.044 | 11.63s | |
| Object Detection (high) | 66.0% ±0.7, Mean of 3 runs, range 65.2 to 66.5 | #16 of 30 | $0.061 | 18.75s | |
| Counting (low) | 76.6% ±1.3, Mean of 3 runs, range 75.7 to 78.4 | #10 of 62 | $0.024 | 10.98s | |
| Counting (high) | 79.7% ±1.4, Mean of 3 runs, range 78.4 to 81.1 | #7 of 30 | $0.043 | 22.28s | |
| Identification (low) | 92.7% ±1.6, Mean of 3 runs, range 90.6 to 93.8 | #12 of 62 | $0.014 | 6.50s | |
| Identification (high) | 90.6% ±0.0, Mean of 3 runs, range 90.6 to 90.6 | #10 of 30 | $0.023 | 11.46s | |
| OCR (low) | 74.3% | #5 of 46 | $0.034 | 12.30s | |
| |||||
| OCR (high) | 76.0% | #6 of 46 | $0.059 | 23.46s | |
| |||||
| Reasoning (low) | 85.2% ±0.3, Mean of 3 runs, range 84.8 to 85.4 | #2 of 62 | $0.024 | 10.78s | |
| Reasoning (high) | 83.4% ±0.7, Mean of 3 runs, range 82.8 to 84.1 | #6 of 49 | $0.047 | 21.70s | |
Overall benchmark score against estimated cost per sample, on a log scale. Upper-left is the sweet spot: high quality at low cost.
61 models on the current benchmark · scores and efficiency pooled across all five tasks at low effort · Muse Wonder highlighted
Muse Wonder scores are the mean of 3 runs per task at both low and high effort; OCR is a single preliminary run · Methodology
View all Vision Evals →Muse Wonder costs $4.00 per 1M input tokens and $20.00 per 1M output tokens.
Pricing updated Oct 13, 2026
Muse Wonder is proprietary: the weights are not distributed, and the Muse Wonder 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 an open model instead of Muse Wonder, Roboflow's licensing page lists the models whose commercial license is included when you deploy on Roboflow.
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 Wonder accepts image input and handles OCR, object counting, identification, visual reasoning, and object detection. On Roboflow's Vision Evals its strongest task is Reasoning at 85.2% (#2 of 62 at low effort).
Yes, and it is one of the model's strongest vision skills: it scores 74.3% (#5 of 46 at low effort) on Vision Evals OCR, which covers single readings, full transcriptions, structured JSON, and locating text with boxes. Within that, full transcriptions score 93.2%, and returning the fields of a label or form as JSON scores 90.5%.
Yes. On Vision Evals, Muse Wonder scores 65.1% mAP@50 on object detection (#15 of 62 at low effort) and 76.6% judge-graded accuracy on object counting.
On our benchmark's task mix, Muse Wonder averages $0.03 per sample at $4.00 per 1M input and $20.00 per 1M output tokens (#60 of 62 on cost), with an average speed of 11.7s per sample across the benchmark. Actual cost depends on your images and prompts.
On the overall Vision Evals ranking, Muse Wonder sits #8 of 62 at 78.8%, just behind Qwen3.8 Max (79.3%) and just ahead of Claude Sonnet 5.5 (77.6%). See the full side-by-side: Muse Wonder vs Qwen3.8 Max.