Skip to main content
leaderboard
.cn
Toggle Sidebar
Search models or organizations…
⌘K
Explore
Frontier Models
Historical Trends
Local Models
Compare Models
Ranking Studio
Library
Models
Pricing
Organizations
Benchmarks
Data sources
Settings
Toggle Sidebar
leaderboard
.cn
Loading page content
Feedback
Loading page content
Back to models
Muse Spark 1.3
Closed
Share
Add to comparison
Tool use · Reasoning
Overview
Pricing
Evaluations
Evaluation overview
Overall rank
#4
97.4 points · 200 models
Long context rank
#1
100 points · 94 models
Data coverage
11 items
1 source · updated through 2026-09-02
Domain performance
Coding
#3 / 180
96.5
Research
#5 / 194
93.3
Agents
#6 / 146
93.2
Long context
#1 / 94
100
Evaluation highlights
All evaluations
DeepSWE 1.1
Coding · Meta Muse Spark 1.3 Official Benchmark · max mode
75.4%
1
/ 33
Terminal-Bench 2.1
Agents · Meta Muse Spark 1.3 Official Benchmark · max mode
88.8%
1
/ 30
GDPval-AA v2
Reasoning · Meta Muse Spark 1.3 Official Benchmark · max mode
1,754pts
6
/ 30
MRCR 256K-512K
Long context · Meta Muse Spark 1.3 Official Benchmark · max mode
98.5%
1
/ 3
JobBench
Agents · Meta Muse Spark 1.3 Official Benchmark · max mode
64.9%
2
/ 21
AutomationBench
Agents · Meta Muse Spark 1.3 Official Benchmark · max mode
49.4%
4
/ 26
Basic information
Context (input / output)
1M / -
Release date
2026-09
Input modalities
Text · Image · Video · PDF
Output modalities
Text
Exact release date
2026-09-02
Positioning
Agentic workflows and long-horizon coding
API model ID
muse-spark-1.3
Availability
Meta Model API
Full pricing
Input
$1.25 /1M
Output
$4.25 /1M
Related links
Official site
Version relationships
Muse-Spark-1.3 family
Muse Spark 1.2
2026-08 · Predecessor
Muse Spark 1.3
Current
2026-09 · Current model