Muse Spark 1.3 (Low): benchmark results
Provider: Meta. Released 2026-09-02. Access: API.
Aggregate Rating 1724 ± 26, rank #328 of 2286 rated models, from 21 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| ObviousBench | 99.31 | Answer pass³ (%) | 89.9 |
| Thrive Helpdesk - Difficult Tickets | 36.54 | Correct ticket resolution (%) | 32.1 |
| Web Clone Bench v1 - Slack | 4.9 | Full score on the Slack clone (%) | 23.1 |
| Web Clone Bench v1 - Zendesk | 1.7 | Full score on the Zendesk clone (%) | 23.1 |
| cua-speedrun - OSWorld (50 Tasks) | 67.62 | Mean verifier score (%), partial credit over the task set | 20 |
| Bug Hunt Bench - VS Code Extension | 5 | Planted Bugs Fixed (out of 45) | 18.7 |
| Web Clone Bench v1 - Sheets | 0.4 | Full score on the Sheets clone (%) | 14.1 |
| Argo-Bench | 15.15 | Mean task score (0-100) over 210 enterprise data-science tas | 13.4 |
| Web Clone Bench v1 - Craigslist | 0 | Full score on the Craigslist clone (%) | 12.8 |
| Bug Hunt Bench | 9.7 | Planted Bugs Fixed (out of 105) | 11.9 |
| Epoch AI - Cursorbench | 29.3 | Score | 11.8 |
| Argo-Bench - Solved | 5.71 | Share of the 210 tasks solved (%), a task counting as solved | 11.6 |
Interactive version: theaggregate.ai/model?slug=muse-spark-1-3-low · How It Works · Data refreshed daily, snapshot 2026-11-20.