Muse Spark 1.1: benchmark results
Meta's Muse Spark 1.1 model, an updated release of the closed Muse Spark system. Provider: Meta. Released 2026-07-09. Access: API.
Aggregate Rating 1821 ± 8, rank #52 of 1656 rated models, from 307 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LLM Stats (CharXiv-R) | 88.4 | Score (%) | 100 |
| SEAL - MultiNRC | 65.59 | Score | 100 |
| SEAL - SWE-Bench Pro (Private Dataset) | 51.5 | Score | 100 |
| SEAL - SWE-Bench Pro (Public Dataset) | 61.5 | Score | 100 |
| SEAL - VisualToolBench (VTB) | 44.77 | Score | 100 |
| TaxEval v2 | 79.72 | Score (%) | 100 |
| Vals AI TaxEval v2 | 79.72 | Accuracy (%) | 99.3 |
| Chatbot Arena (Text - Polish) | 1507 | Arena Score | 98.7 |
| Chatbot Arena (Text - French) | 1515 | Arena Score | 98.1 |
| SEAL - MCP Atlas | 88.1 | Score | 98.1 |
| Arabic Broad Leaderboard - Trust & Safety | 10 | Average Score (0-10) | 97.9 |
| Chatbot Arena (Text - Business, Management & Financial Ops) | 1492 | Arena Score | 97.8 |
Interactive version: theaggregate.ai/model?slug=muse-spark-1-1 · How It Works · Data refreshed daily, snapshot 2026-10-20.