Compare / OpenAI dots vs Cue by Manus
OpenAI dots vs Cue by Manus
OpenAI dots is a persistent personal agent from OpenAI (United States); Cue by Manus is an independent identity, multi-agent collaborative personal execution agent from Manus (Singapore). PersonalAgentEval reports 55.9% resolved for OpenAI dots and 19.1% for Cue by Manus, across 152 scoring units from 132 task chains in simulated accounts; these are source results, not PAEval ratings. PAEval holds 31 capability records for OpenAI dots and 18 for Cue by Manus (as of 28 Oct 2026).
Scores stay on each evaluator's own scale and are never combined. PAEval does not pick a winner.
| OpenAI dots | Cue by Manus | |
|---|---|---|
| Vendor | OpenAI | Manus |
| HQ region | United States | Singapore |
| Type | Persistent personal agent | Independent identity, multi-agent collaborative personal execution agent |
| Pricing (as documented) | The first dot is included in Pro, with no independent surcharge; Pro is currently 100/200/500 US dollars per month, and 500 includes… | An invitation code is required; the official App Store says registration is free and Plus is free after being invited. The store has SKU,… |
| Assistant Benchmark1–10 mean of scored dimensions | 8.4coverage 7/15 | Not scored |
| micro1 PersonalAgentBench% of 10 workflows with trusted completion | Not scored | Not scored |
| SuperCLUE-XClaw0–100 weighted total of 5 dimensions | Not scored | Not scored |
| PersonalAgentEval% resolved across 152 scoring units (132 task chains) | 55.9%95% CI 48.1–63.5% · coverage 152 scoring units / 132 task chains | 19.1%95% CI 13.0–25.5% · coverage 152 scoring units / 132 task chains |
| Autonomy & background work | Documented | Limited or conditional |
| Execution environments | Documented | Limited or conditional |
| Calls, messages & identity | Limited or conditional | Limited or conditional |
| Connectors & tools | Limited or conditional | Limited or conditional |
| Memory & personalization | Documented | Documented |
| Channels & interfaces | Documented | Documented |
| Research & deliverables | Limited or conditional | Partly disclosed / partly tested |
| Transactions & bookings | Limited or conditional | No record |
| Collaboration & parallelism | Limited or conditional | Documented |
| Reliability & recovery | Documented | Partly disclosed / partly tested |
| Permissions, security & data | Documented | Documented |
| Capability records | 31 (0 independent) | 18 (1 independent) |
Capability cells show the strongest documented or observed status in each domain; availability is not task success.Add more products →