Roboflow

Muse Ember vs Muse Spark 1.1

Muse Ember and Muse Spark 1.1 score 76.6% vs 74.4% averaged across five Vision Evals tasks (#22 and #24 of 73 models), so Muse Ember leads overall.

  • Muse Ember wins 4 of the 5 tasks, with its widest lead on reasoning (78.2% vs 74.2%).
  • Muse Ember is about 1/8 of the cost: $0.0009 vs $0.0075 overall average cost per sample.
  • Muse Ember is faster: 6.1s vs 7.2s per sample.

Compare Muse Ember vs Muse Spark 1.1 live

Run the same image across every model that supports a task and compare their outputs side-by-side.

These models don't share enough common tasks for a side-by-side demo. See the comparison table below for their capabilities.

Muse Ember vs Muse Spark 1.1 on Vision Evals

Score by taskMuse EmberMuse Spark 1.1
Reasoning
78.2
74.2
Object Detection
63.8
60.6
Counting
79.7
76.6
OCR
69.5
68.8
Identification
91.7
91.7

Roboflow Vision Evals. Full breakdown below.

Muse Ember vs Muse Spark 1.1 Comparison Table

Evals updated November 19, 2026Pricing updated November 21, 2026

PropertyMuse EmberMuse Spark 1.1
OrganizationMetaMeta
Categoryclosedclosed
Modalitymultimodalmultimodal
Release DateNov 2026Jul 2026
Context Window1.0M1.0M
ParametersUnknownUnknown
LicenseProprietaryProprietary
Commercial usecommercial use per vendor termscommercial use per vendor terms
Pricing per 1M tokens
Input $/1M$0.100$1.25
Output $/1M$0.500$4.25
Vision Tasks
CaptioningSupportedDemo
ClassificationSupportedDemo
Object DetectionSupportedDemo
OCRSupportedDemo
Visual Question AnsweringSupportedDemo
Both support 5 more tasks
Model Features
Both support 3 more features
Vision Evalsground-truth scores across 5 vision tasks, pooled at low effort
Overall
76.6%
74.4%
Avg cost / sample$0.0009$0.0075
Avg speed / sample6.08s7.15s
By task
Object Detection (low)
63.8%
±0.5, Mean of 3 runs, range 63.3 to 64.3
$0.0011
60.6%
±1.9, Mean of 3 runs, range 58.4 to 62.1
$0.0097
Object Detection (high)
64.0%
±0.5, Mean of 3 runs, range 63.5 to 64.5
$0.0017
60.0%
±0.5, Mean of 3 runs, range 59.6 to 60.7
$0.015
Counting (low)
79.7%
±1.4, Mean of 3 runs, range 78.4 to 81.1
$0.0006
76.6%
±1.3, Mean of 3 runs, range 75.7 to 78.4
$0.0042
Counting (high)
79.3%
±0.7, Mean of 3 runs, range 78.4 to 79.7
$0.0011
76.1%
±0.7, Mean of 3 runs, range 75.7 to 77.0
$0.0079
Identification (low)
91.7%
±1.6, Mean of 3 runs, range 90.6 to 93.8
$0.0004
91.7%
±1.6, Mean of 3 runs, range 90.6 to 93.8
$0.0033
Identification (high)
90.6%
±3.1, Mean of 3 runs, range 87.5 to 93.8
$0.0007
89.6%
±1.6, Mean of 3 runs, range 87.5 to 90.6
$0.0065
OCR (low)
69.5%
$0.0010
68.8%
$0.0076
by category
Single value
61.7%
Transcription
95.5%
Structured JSON
85.1%
Text localization
35.3%
Single value
60.4%
Transcription
90.1%
Structured JSON
86.1%
Text localization
33.9%
OCR (high)
70.5%
$0.0017
67.5%
$0.015
by category
Single value
63.0%
Transcription
90.2%
Structured JSON
87.2%
Text localization
35.9%
Single value
60.4%
Transcription
81.6%
Structured JSON
85.7%
Text localization
31.4%
Reasoning (low)
78.2%
±1.3, Mean of 3 runs, range 76.8 to 79.5
$0.0006
74.2%
±1.7, Mean of 3 runs, range 72.2 to 75.5
$0.0061
Reasoning (high)
81.9%
±1.7, Mean of 3 runs, range 80.1 to 83.4
$0.0013
76.6%
±1.3, Mean of 3 runs, range 75.5 to 78.2
$0.013

Muse Ember vs Muse Spark 1.1: Overview

Muse Ember

Muse Ember is a proprietary multimodal reasoning model from Meta, released on November 9, 2026. It accepts text, images, video, audio, and PDF documents and returns text. The Meta Model API serves it as muse-ember-1.0, with a 1,048,576-token context window and up to 524,288 output tokens. Reasoning effort is adjustable from minimal to max.

Meta positions Ember for repeated tasks within larger agent workflows: tool calls, routing, coding subtasks, and processing collections of images and documents. It can caption or sort photos and extract fields from records while a larger Muse model handles planning. Meta recommends Spark or Wonder for harder single-shot coding and knowledge-heavy problems. Ember is available as a hosted model; its weights are not publicly released.

Muse Spark 1.1

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.