Muse Spark 1.3 (High): benchmark results
Provider: Meta. Released 2026-09-02. Access: API.
Aggregate Rating 1798 ± 14, rank #144 of 2170 rated models, from 84 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Korean CSAT 2026 (Easy Mode) - Physics I | 50 | Points (out of 50) | 96 |
| Korean CSAT 2026 (Easy Mode) - Society and Culture | 46 | Points (out of 50) | 92 |
| Korean CSAT 2026 (Easy Mode) - Life Science I | 50 | Points (out of 50) | 91.3 |
| Korean CSAT 2026 (Easy Mode) - Chemistry I | 50 | Points (out of 50) | 91 |
| ObviousBench | 99.31 | Answer pass³ (%) | 89.9 |
| Korean CSAT 2026 (Easy Mode) - Total | 442 | Points (out of 450) | 89.3 |
| Korean CSAT 2026 (Easy Mode) - Mathematics | 100 | Points (out of 100) | 88.7 |
| FrontierCS 2 - Approximate-MIPS Query Stopping | 85.93 | Task score (0–100) | 82.4 |
| FrontierCS 2 - SQL Counterexample Search | 96.86 | Task score (0–100) | 76.5 |
| Korean CSAT 2026 (Easy Mode) - Korean | 97 | Points (out of 100) | 71 |
| FrontierCS 2 - E-Graph Invariant Restoration | 60.36 | Task score (0–100) | 70.6 |
| Multi-turn Debate (Lechmazur) | 1590.1 | Bradley-Terry Rating | 70 |
Interactive version: theaggregate.ai/model?slug=muse-spark-1-3-high · How It Works · Data refreshed daily, snapshot 2026-11-05.