Muse Spark 1.1 vs Muse Spark 1.2
Muse Spark 1.1 and Muse Spark 1.2 score 74.4% vs 73.8% averaged across five Vision Evals tasks (#16 and #18 of 65 models), so they are effectively tied.
- Muse Spark 1.1 wins 3 of the 5 tasks, with its widest lead on object detection (60.6% vs 59.0%).
- Muse Spark 1.1 is cheaper: $0.0075 vs $0.0083 overall average cost per sample.
- Muse Spark 1.1 is faster: 7.2s vs 11.5s per sample.
Roboflow Vision Evals. Full breakdown below.
Compare Muse Spark 1.1 vs Muse Spark 1.2 live
Run the same image across every model that supports a task and compare their outputs side-by-side.
Detect and compare bounding boxes across models on the same image.
Upload an image
Drag and drop an image here, or click to browse
Muse Spark 1.1 vs Muse Spark 1.2 on Vision Evals
Roboflow Vision Evals. Full breakdown below.
Muse Spark 1.1 vs Muse Spark 1.2 Comparison Table
Evals updated October 26, 2026Pricing updated November 5, 2026
| Property | Muse Spark 1.1 | Muse Spark 1.2 |
|---|---|---|
| Organization | Meta | Meta |
| Category | closed | closed |
| Modality | multimodal | multimodal |
| Release Date | Jul 2026 | Aug 2026 |
| Context Window | 1.0M | 1.0M |
| Parameters | Unknown | Unknown |
| License | Proprietary | Proprietary |
| Commercial use | commercial use per vendor terms | commercial use per vendor terms |
| Pricing per 1M tokens | ||
| Input $/1M | $1.25 | $1.25 |
| Output $/1M | $4.25 | $4.25 |
| Vision Tasks | ||
| Model Features | ||
Both support 3 more features | ||
Vision Evalsground-truth scores across 5 vision tasks, pooled at low effort | ||
| Overall | 74.4% | 73.8% |
| Avg cost / sample | $0.0075 | $0.0083 |
| Avg speed / sample | 7.15s | 11.51s |
| By task | ||
| Object Detection (low) | 60.6% ±1.9, Mean of 3 runs, range 58.4 to 62.1 | 59.0% ±1.0, Mean of 3 runs, range 58.1 to 60.2 |
| Object Detection (high) | 60.0% ±0.5, Mean of 3 runs, range 59.6 to 60.7 | 60.5% ±0.3, Mean of 3 runs, range 60.2 to 60.7 |
| Counting (low) | 76.6% ±1.3, Mean of 3 runs, range 75.7 to 78.4 | 76.6% ±2.7, Mean of 3 runs, range 74.3 to 79.7 |
| Counting (high) | 76.1% ±0.7, Mean of 3 runs, range 75.7 to 77.0 | 75.2% ±2.0, Mean of 3 runs, range 73.0 to 77.0 |
| Identification (low) | 91.7% ±1.6, Mean of 3 runs, range 90.6 to 93.8 | 89.6% ±1.6, Mean of 3 runs, range 87.5 to 90.6 |
| Identification (high) | 89.6% ±1.6, Mean of 3 runs, range 87.5 to 90.6 | 87.5% ±0.0, Mean of 3 runs, range 87.5 to 87.5 |
| OCR (low) | 68.8% | 68.7% |
| by category |
|
|
| OCR (high) | 67.5% | 68.6% |
| by category |
|
|
| Reasoning (low) | 74.2% ±1.7, Mean of 3 runs, range 72.2 to 75.5 | 75.1% ±0.3, Mean of 3 runs, range 74.8 to 75.5 |
| Reasoning (high) | 76.6% ±1.3, Mean of 3 runs, range 75.5 to 78.2 | 75.7% ±0.3, Mean of 3 runs, range 75.5 to 76.2 |
Muse Spark 1.1 vs Muse Spark 1.2: Overview
Muse Spark 1.1 is a natively multimodal reasoning model from Meta Superintelligence Labs, released on July 9, 2026, as a significant upgrade to the original Muse Spark. The model accepts text, image, video, PDF, and audio as input and produces text output. It operates with a 1-million-token context window (1,048,576 tokens per the Meta Model API documentation) and is designed specifically for agentic tasks that require planning, tool use, computer use, and multi-agent orchestration. The model runs in a "Thinking" mode, where adjustable reasoning effort is applied before generating a response. It can function both as a main agent gathering context, forming plans, and delegating to parallel subagents and as a subagent that adheres to assigned tasks and escalates when needed. It is trained to decide autonomously when to write automation scripts versus interact directly with a user interface.
Muse Spark 1.1 supports a range of multimodal capabilities including visual perception, image and video captioning, visual-to-code generation, and document analysis. The model was evaluated under Meta's Advanced AI Scaling Framework across frontier risk categories including chemical and biological threats, cybersecurity, and loss-of-control scenarios. Parameter count, architecture details, and training data composition are not publicly disclosed. The model is proprietary and closed-weight, accessible to consumers through the Meta AI app and to developers via the Meta Model API, which launched in public preview alongside this release.
Muse Spark 1.2 is a proprietary multimodal reasoning model from Meta Superintelligence Labs, released as a coding-focused update to Muse Spark 1.1. It accepts text, images, video, audio, and PDF documents and returns text, with a context window of roughly one million tokens that allows whole repositories, long documents, and extended agent trajectories to be held in a single request. The model thinks before answering, and the amount of reasoning effort it spends is configurable per request. Alongside its visual and document understanding, it supports structured output and parallel function calling, and it is designed to operate either as a planning agent that delegates work or as a subagent executing tasks in parallel.
Training for version 1.2 scaled up compute on coding tasks and widened the diversity of training environments, concentrating on long-horizon work such as whole-repository generation, large end-to-end projects, and automated research. Part of the training data was self-generated, with Muse Spark 1.1 producing coding environments and instruction-following templates and grading candidate solutions against them. The model was co-trained with the Muse Code terminal agent, incorporating rejection-sampled harness trajectories and that toolset. Multimodal use cases documented for the family include visual-to-code generation and detailed image and video captioning.
Frequently Asked Questions
On Roboflow's Vision Evals, Muse Spark 1.1 performed better. It scores higher on 3 of the five vision tasks and averages 74.4% (#16 of 65) against 73.8% (#18 of 65) for Muse Spark 1.2. These scores measure vision capabilities only; either model may perform differently on work outside this benchmark's tasks.
Yes. On the Vision Evals Identification benchmark at low effort, Muse Spark 1.1 leads with 91.7% against 89.6%. This is the widest gap between the two models across the benchmark's tasks.
Muse Spark 1.1 is cheaper to run. Across Roboflow's Vision Evals task mix it averaged $0.0075 per sample against $0.0083. Muse Spark 1.1 is priced at $1.25 per 1M input tokens and $4.25 per 1M output; Muse Spark 1.2 is priced at $1.25 per 1M input tokens and $4.25 per 1M output. Actual costs depend on your image sizes, prompts, and output length.
Muse Spark 1.1 is faster. Across Roboflow's Vision Evals it averaged 7.2s per inference against 11.5s. 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 OCR and image classification in the free Roboflow Playground. You can try it instantly, and a free account unlocks unlimited runs.