Start free trial

TRUE, BUTCherry-Picked Slice

The most frontier model resisted 97%

The '97% of frontier models get jailbroken' stat comes from a study where the most frontier model resisted 97% of the time.

“Reasoning models now jailbreak frontier LLMs autonomously at a 97% success rate”

Security-statistics aggregators amplifying the Hagendorff et al. Nature Communications study (SQ Magazine and others), 5 February 2026

Recorded 14 August 2026. Our ruling means: literally true, materially misleading.

Read the story →

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.

The receipts

Each source, the line we quote from it, its date and which way it cuts. Free to read and to cite.

  1. 1Supports the claimsqmagazine.co.uk ↗

    Multi-turn jailbreaks hit 97% success on frontier LLMs.

    Look up an archived copy ↗

  2. 2Contradicts the claimnature.com ↗

    Claude 4 Sonnet is by far the most resistant model, receiving the highest harm score in only a fraction of benchmark items across adversarial models (2.86%)

    Look up an archived copy ↗

  3. 3Contextweb.archive.org ↗

    the persuasive capabilities of large reasoning models (LRMs) simplify and scale jailbreaking, converting it into an inexpensive activity accessible to non-experts

    Look up an archived copy ↗

Members' extras

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

  • What each receipt above proves, in our words
  • 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 receipt above stay free. Membership adds our analysis to the evidence file for every checked story.

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.