Compare / Town vs Shuffle
Town vs Shuffle
Town is a work-based personal agents and team automation from Town.com (United States); Shuffle is a creation/entertainment companion assistant, including website execution from DNFT (United States). On Assistant Benchmark (1–10, updated 8 Oct 2026), Town scores 8.3 over 7 dimensions and Shuffle scores 7.8 over 10; both were scored on 6 of the same dimensions, shown below. PAEval holds 15 capability records for Town and 14 for Shuffle (as of 9 Oct 2026).
Scores stay on each evaluator's own scale and are never combined. PAEval does not pick a winner.
| Town | Shuffle | |
|---|---|---|
| Vendor | Town.com | DNFT |
| HQ region | United States | United States |
| Type | Work-based personal agents and team automation | Creation/entertainment companion assistant, including website execution |
| Pricing (as documented) | Not compiled | Pro $8/month: Unlimited chat + 880 monthly picture/video/music credits; $1 daily pass and $4.99 weekly pass are unlimited chat. |
| Assistant Benchmark1–10 mean of scored dimensions | 8.3coverage 7/15 | 7.8coverage 10/15 |
| micro1 PersonalAgentBench% of 10 workflows with trusted completion | Not scored | Not scored |
| SuperCLUE-XClaw0–100 weighted total of 5 dimensions | Not scored | Not scored |
| Autonomy & background work | Documented | Partly disclosed / partly tested |
| Execution environments | Partly disclosed / partly tested | Documented |
| Calls, messages & identity | Documented | Partly disclosed / partly tested |
| Connectors & tools | Documented | Not disclosed |
| Memory & personalization | Documented | Documented |
| Channels & interfaces | Documented | Documented |
| Research & deliverables | Documented | Documented |
| Transactions & bookings | No record | No record |
| Collaboration & parallelism | Documented | Documented |
| Reliability & recovery | Documented | Independently observed |
| Permissions, security & data | Documented | Documented |
| Capability records | 15 (1 independent) | 14 (1 independent) |
Capability cells show the strongest documented or observed status in each domain; availability is not task success.Add more products →
Assistant Benchmark, dimension by dimension
| Town | Shuffle | |
|---|---|---|
| Carrying out an online task | Not tested | 7.5test |
| Travel booking | Not tested | 9test |
| Recommendation quality | 8test | 9test |
| Purchasing a product | Not tested | 8test |
| Responding to emails | 8test | 8test |
| Proactive behavior | Not tested | Not tested |
| Running a routine | 7test | Not tested |
| Third-party integrations | 10observed in use | 7test |
| Permissions & privacy | 8observed in use | 7test |
| Memory | 8unlabelled | 6test |
| Phone calls | Not tested | n/a |
| Multiplayer / groups | Not tested | n/a |
| Chained tasks | Not tested | 7test |
| Proactive restraint | Not tested | Not tested |
| Content creation / games | 9test | 9test |
Source scores on the 1–10 anchor scale. "Not tested" is missing evidence, not zero.Source ↗