Roboflow

Muse Ember vs Muse Spark 1.3

Muse Ember and Muse Spark 1.3 score 76.6% vs 73.9% averaged across five Vision Evals tasks (#22 and #25 of 73 models), so Muse Ember leads overall.

  • Muse Ember wins 3 of the 5 tasks, with its widest lead on counting (79.7% vs 74.3%).
  • Muse Ember is about 1/9 of the cost: $0.0009 vs $0.0084 overall average cost per sample.
  • Muse Ember is faster: 6.1s vs 25.5s per sample.

Compare Muse Ember vs Muse Spark 1.3 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 1.3 on Vision Evals

Score by taskMuse EmberMuse Spark 1.3
Counting
79.7
74.3
Object Detection
63.8
58.6
Reasoning
78.2
73.3
Identification
91.7
92.7
OCR
69.5
70.4

Roboflow Vision Evals. Full breakdown below.

Muse Ember vs Muse Spark 1.3 Comparison Table

Evals updated November 19, 2026Pricing updated November 20, 2026

PropertyMuse EmberMuse Spark 1.3
OrganizationMetaMeta
Categoryclosedclosed
Modalitymultimodalmultimodal
Release DateNov 2026Sep 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%
73.9%
Avg cost / sample$0.0009$0.0084
Avg speed / sample6.08s25.50s
By task
Object Detection (low)
63.8%
±0.5, Mean of 3 runs, range 63.3 to 64.3
$0.0011
58.6%
±0.7, Mean of 3 runs, range 58.0 to 59.4
$0.011
Object Detection (high)
64.0%
±0.5, Mean of 3 runs, range 63.5 to 64.5
$0.0017
56.6%
±2.4, Mean of 3 runs, range 54.5 to 59.3
$0.017
Counting (low)
79.7%
±1.4, Mean of 3 runs, range 78.4 to 81.1
$0.0006
74.3%
±2.0, Mean of 3 runs, range 73.0 to 77.0
$0.0049
Counting (high)
79.3%
±0.7, Mean of 3 runs, range 78.4 to 79.7
$0.0011
75.7%
±3.4, Mean of 3 runs, range 73.0 to 79.7
$0.0094
Identification (low)
91.7%
±1.6, Mean of 3 runs, range 90.6 to 93.8
$0.0004
92.7%
±1.6, Mean of 3 runs, range 90.6 to 93.8
$0.0036
Identification (high)
90.6%
±3.1, Mean of 3 runs, range 87.5 to 93.8
$0.0007
86.5%
±1.6, Mean of 3 runs, range 84.4 to 87.5
$0.0063
OCR (low)
69.5%
$0.0010
70.4%
$0.0086
by category
Single value
61.7%
Transcription
95.5%
Structured JSON
85.1%
Text localization
35.3%
Single value
62.6%
Transcription
91.8%
Structured JSON
88.0%
Text localization
33.3%
OCR (high)
70.5%
$0.0017
69.8%
$0.015
by category
Single value
63.0%
Transcription
90.2%
Structured JSON
87.2%
Text localization
35.9%
Single value
62.2%
Transcription
86.8%
Structured JSON
87.2%
Text localization
35.2%
Reasoning (low)
78.2%
±1.3, Mean of 3 runs, range 76.8 to 79.5
$0.0006
73.3%
±1.0, Mean of 3 runs, range 72.2 to 74.2
$0.0064
Reasoning (high)
81.9%
±1.7, Mean of 3 runs, range 80.1 to 83.4
$0.0013
73.1%
±1.0, Mean of 3 runs, range 72.2 to 74.2
$0.012

Muse Ember vs Muse Spark 1.3: 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 1.3

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. Prior Muse Spark versions emit bounding box coordinates, transcriptions, and structured field extractions from images on Roboflow Vision Evals.