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
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LLM Stats (AutomationBench) | 49.4 | Score (%) | 100 |
| LLM Stats (DeepSWE 1.1) | 75.4 | Score (%) | 100 |
| LLM Stats (Job Bench) | 64.9 | Score (%) | 100 |
| LLM Stats (MRCR v2 (8-needle)) | 98.5 | Score (%) | 100 |
| Design Arena (Website) | 1342 | Elo | 99.4 |
| BenchmarkList ECI | 153.15 | Capability Index (ECI) | 98.9 |
| LLM Stats Score | 55.31 | LLM Stats Score (conservative rating) | 98.9 |
| ComplexConstraints | 50.8 | Score (%) | 98.6 |
| SimpleBench | 81.8 | Score (AVG@5) | 96 |
| LLM Stats (Terminal-Bench 2.1) | 88.8 | Score (%) | 95.6 |
| GDP.pdf | 27.6 | Strict Pass Rate (%) | 87.8 |
| AI Chess Leaderboard (Reasoning) | 1242 | Elo | 86.2 |
Interactive version: theaggregate.ai/model?slug=muse-spark-1-3 · How It Works · Data refreshed daily, snapshot 2026-09-05.