Back Back
Models6/day by emailReported

AI models can now win gold at the International Mathematical Olympiad, yet Stanford's 2026 AI Index found they still fumble a task most children master early. Across ClockBench's 180 clock designs and 720 questions, the top model, GPT-5.4 High, read analog clocks correctly only 50.6% of the time, versus 90.1% for humans

Stanford's AI Index 2026 report notes that AI models still struggle with some basic tasks. On ClockBench, which uses 180 clock designs and 720 questions, the top model, GPT-5.4 High, read analog clocks correctly 50.6% of the time in March 2026. Humans got 90.1% right on the same task.

SourceStanford AI Index·2026 AI Index Report

Verified 2026-09-08

Track with Insider

Why it matters

Strong scores on hard tests do not guarantee common sense, so treat headline benchmark wins with some care.

FREE · NO CARD

Facts like this, six days a week

The Daily Receipts on weekdays, The Weekly Brief on Saturday — six sourced facts a day by email, two more than the free site shows. Every one traced to the filing it came from. Free.

Get the free daily brief

Free · No card · Unsubscribe anytime

Join now and you start with 100 Receipts on The Receipts Ledger — your first step toward a free year of Insider or Pro. How it works →

See today's issue →