Benchmark tests 71 AI personal assistants across 15 dimensions, Muse tops at 9.1
ai · x · 2026-09-15
Assistant Benchmark scored 71 AI personal assistants 1–10 across 15 dimensions—online tasks, travel, shopping, email, proactivity, memory, phone calls and more—after real use. Muse leads with 9.1 overall (7s responses), followed by Instinct (8.4) and szn (8.0). The site logs concrete test cases, e.g. Asaply stopping a purchase before charging and declining email tasks outside its scope. Median reply time is 11s; most assistants still struggle with multi-step tasks and group chats.
More from Apps
- Matt Shumer rebuilds his workflow around t3dotcodes, will share the full playbook — mattshumer_ · 2026-09-15
- Andon Labs Launches Pion, Agents That Run Fully Autonomous Companies — infoxiao · 2026-09-15
- Apple ships iOS 26.7 alongside iOS 27, dev calls versioning weird and UI confusing — Dimillian · 2026-09-15
- Photo of fridge whiteboard list becomes a full Sam's Club order via Muse agent — armand_ruiz · 2026-09-15
- Google's Gemini power user group has tested 20+ early features; new cohort opens for Daily Brief — GeminiApp · 2026-09-15
- CapCut PC adds Seedance 2.5 with a staged storyboard-to-video workflow up to 30s — Div_pradeep · 2026-09-15