Muse Ember (Max): benchmark results
Provider: Meta. Released 2026-11-09. Access: API.
Aggregate Rating 1831 ± 15, rank #100 of 2201 rated models, from 81 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AutomationBench-AA - HR - Raw Objective Completion | 80.95 | Raw Objective Completion (%) | 98 |
| AA-Omniscience v1.1 Hallucination Rate | 17.36 | Hallucination Rate (%) | 96.2 |
| Vals AI Harvey Legal Agent Bench v1.1 | 25 | Task Resolution (%) | 95.8 |
| AutomationBench-AA - Operations - Raw Objective Completion | 96.51 | Raw Objective Completion (%) | 95.1 |
| AutomationBench-AA - Finance - Raw Objective Completion | 90.69 | Raw Objective Completion (%) | 94.9 |
| AutomationBench-AA - Marketing - Raw Objective Completion | 89.5 | Raw Objective Completion (%) | 94.9 |
| AA GDP.pdf - Manufacturing/Supply Chains - Criterion Pass Rate | 78.86 | Criterion Pass Rate (%) | 94.1 |
| AutomationBench-AA | 68.08 | Guardrail-Adjusted Objective Completion (%) | 93.7 |
| AutomationBench-AA - Strict | 37.75 | Strict Task Success (%) | 92.9 |
| AA GDP.pdf - Legal - Criterion Pass Rate | 84.73 | Criterion Pass Rate (%) | 91.7 |
| AA GDP.pdf - Real Estate - Criterion Pass Rate | 74.53 | Criterion Pass Rate (%) | 91.7 |
| Vals AI Legal Index | 75.69 | Legal Index (%) | 91.7 |
Interactive version: theaggregate.ai/model?slug=muse-ember-max · How It Works · Data refreshed daily, snapshot 2026-11-12.