Muse Spark 1.1 (High): benchmark results

Provider: Meta. Released 2026-07-09. Access: API.

Aggregate Rating 1790 ± 28, rank #157 of 2168 rated models, from 16 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
ObviousBench98.61Answer pass³ (%)86.9
Multi-turn Debate (Lechmazur)1633.9Bradley-Terry Rating82.8
Epoch AI - Dtbench94.4Score76.3
Meta Muse Spark 1.1 Report - GDM Situational Awareness - Average Success Rate55.1Average Success Rate (%)75
Meta Muse Spark 1.1 Report - GDM Stealth - Classifier Evasion1.6Success Rate (%)75
Conceptual Reasoning Index - Argument Evaluation (LMCA)49.91Chance-Corrected Score (0-100)73.7
Creative Writing (Lechmazur)0.76Mean Score65.5
Lech Mazur Writing0.76Comparison Score (points)65.5
Surface Evolver Bench Pass Rate37.5Pass Rate (%)63
Context Arena58.46Average Score (%)59.3
Meta Muse Spark 1.1 Report - GDM Stealth - Cover Your Tracks18.1Success Rate (%)50
Meta Muse Spark 1.1 Report - GDM Stealth - Oversight Pattern65.5Success Rate (%)50

Interactive version: theaggregate.ai/model?slug=muse-spark-1-1-high · How It Works · Data refreshed daily, snapshot 2026-10-20.