TRUE, BUT

The '59.4% of SWE-bench is broken' stat comes from an audit that only examined the problems OpenAI's own model kept failing.

Eval roundups and tech aggregators compressing OpenAI's February 2026 retirement post from spring onward (byteiota and others). Recorded 14 August 2026. Our ruling means: literally true, materially misleading.

Read the story and its public receipts →

Receipts pack

The evidence file for this verdict

3 receipts: 1 support the claim, 1 contradict it, 1 add context. 3 figures on the record, 1 traced to a quoted receipt.

1web.archive.org ↗Every source link and quote stays open on the story page.
2
3

Members get the full file

What each receipt proves, and what would change our mind.

Every receipt with its source, date and stance, plus what it proves
The figures table, each number traced to the receipt that states it
The trick behind the claim, explained, with the guide to spotting it
What would change our verdict
Our call on the record, with its due date

The verdict, the opening and every source link stay free. Membership opens the evidence file for every checked story.

See Membership →Already a member? Sign in →

First membership: 30 days free, then A$89 a year. One introductory trial per customer. Card required; renews annually until cancelled. Cancel before the trial ends to avoid the first charge.