PUBLISHED BENCHMARKS
| deepSwe | 75.4 |
|---|
Meta reported · 2026-09
MODEL / MUSE-SPARK-1-3
Muse Spark 1.3
Meta's frontier — reported 75.4% DeepSWE v1.1 at max reasoning.
model
textcodereasoning
Kindmodel
Access—
Pricing—
Free tier—
Caps3
MACHINE-READABLE
GET /api/v1/resources/muse-spark-1-3Open JSON ↗