Observed arrival · 2026-09-09
Assistant Benchmark's public scorecard
A comparative scorecard that evaluates textable AI assistants across 15 dimensions, from travel booking and email to memory, restraint, and phone calls.
Why it surfaced
Assistant Benchmark turns real-use tests into a public table of 54 assistants, with scores, response times, and published test notes. Its travel entries document assistants searching hotels, handling price changes, collecting traveler details, and stopping before payment—far more revealing than a leaderboard built from synthetic prompts.
A comparative scorecard that evaluates textable AI assistants across 15 dimensions, from travel booking and email to memory, restraint, and phone calls.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
One card from the complete issue