Head to head
Poke vs Brea
Same 15 tests, same scale. The check goes to the higher score.
Poke1–0Across 2 tested dimensions, 1 tie.
Brea3Asked to accept a calendar invite; could not, and pointed to the calendar app instead.
3Asked to book a Loop hotel under $250 with free cancel; listed Canopy and Central Loop, then said it cannot stage a reservation.
8Pulled three months of connected health data and gave specific, evidence-backed recommendations.
7Asked for a Loop dinner for four under $40 with veg and no chains; got Dearborn, Gage, and ema, with ema flagged as a restaurant group.
8Swept the guest-post backlog, listed four open pricing inquiries and who was owed a deliverable, then archived the rest and set a rule.
7Reminder set, rescheduled twice on request and fired on time, interleaved with seven unsolicited digests.
7Weekday 7am briefing fired on time both mornings with the calendar and owed replies; the weather followed about an hour later each day.
7Created a calendar invite with the right title, attendees and video link, confirming before saving, but jumped in before instructions.
6Set a no-email/no-spend rule on Calendar-only; blocked a buy ask, kept email unsent, and disconnect dropped Calendar access.
8Set a timed reminder, immediately checked two code repos with specific findings, and the reminder fired on time with the right items.
2Kept auto-drafting email replies after repeated instructions to stop, then escalated the bug to its own team on request.
Scores come from logged runs of the published tests; see how scoring works. Nothing here is sponsored.