Muse Spark 1.1 (xHigh): benchmark results
Provider: Meta. Released 2026-07-09. Access: API.
Aggregate Rating 1795 ± 12, rank #145 of 2169 rated models, from 127 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Vals AI TaxEval v2 | 79.72 | Accuracy (%) | 99.3 |
| Vals AI CorpFin v2 | 71.29 | Accuracy (%) | 97.7 |
| AA-Omniscience Index - Science, Engineering & Mathematics | 28.08 | Omniscience Index | 97.6 |
| AA-Omniscience Index - Health | 21.02 | Omniscience Index | 97.4 |
| AA GDP.pdf - Legal - Criterion Pass Rate | 84.9 | Criterion Pass Rate (%) | 95.1 |
| Vals AI Harvey Legal Agent Bench | 20 | Accuracy (%) | 95 |
| AA-Omniscience Index - Humanities & Social Sciences | 30.13 | Omniscience Index | 94.7 |
| LiveBench JavaScript | 77.27 | Score | 93.6 |
| AA Humanity's Last Exam | 46.2 | Accuracy (%) | 93.4 |
| AA Omniscience | 28.08 | Score | 93.4 |
| AA-Omniscience Index - Business | 21 | Omniscience Index | 92.7 |
| AA SciCode | 58.8 | Accuracy (%) | 92.6 |
Interactive version: theaggregate.ai/model?slug=muse-spark-1-1-xhigh · How It Works · Data refreshed daily, snapshot 2026-10-23.