Benchmark18 Sep 2026 00:00 UTC · 11d ago

Epoch AI evaluates Muse Spark 1.3

FrontierMath-Tiers-1-3-v2-Private 74.0% · FrontierMath-Tier-4-v2-Private 46.3% · Chess Puzzles 38.0% · Mystery Game Puzzles 25.0%

Type: BENCHMARK_RESULT
Detection: benchmark
Confidence: high
Status

Related entities

ModelMuse Spark 1.3 CompanyMeta

Primary source

Epoch AI Benchmarking Hub · epoch.ai/benchmarks ↗

Independent benchmark runs (GPQA Diamond, SWE-bench Verified, FrontierMath, ...) plus externally reported leaderboards and the Epoch Capabilities Index (ECI).

Related events

Model launch27d ago
Meta releases Muse Spark 1.3
Epoch AI Benchmarking HubMuse Spark 1.3 Meta