Muse Spark 1.3: benchmark results

Provider: Meta. Released 2026-09-02. Access: API.

Unified ELO 1770 ± 1, rank #12 of 1392 rated models, from 28 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
LLM Stats (AutomationBench)49.4Score (%)100
LLM Stats (DeepSWE 1.1)75.4Score (%)100
LLM Stats (Job Bench)64.9Score (%)100
LLM Stats (MRCR v2 (8-needle))98.5Score (%)100
Design Arena (Website)1342Elo99.4
BenchmarkList ECI153.15Capability Index (ECI)98.9
LLM Stats Score55.31LLM Stats Score (conservative rating)98.9
ComplexConstraints50.8Score (%)98.6
SimpleBench81.8Score (AVG@5)96
LLM Stats (Terminal-Bench 2.1)88.8Score (%)95.6
GDP.pdf27.6Strict Pass Rate (%)87.8
AI Chess Leaderboard (Reasoning)1242Elo86.2

Interactive version: theaggregate.ai/model?slug=muse-spark-1-3 · How It Works · Data refreshed daily, snapshot 2026-09-05.