Start free trial

TRUE, BUTSelf-Marked

Its model came first.

“The new Conceptual Reasoning Index, built in collaboration with Anthropic, measures how well models reason about hard-to-verify AI-risk questions; Anthropic's Opus 5 tops it at 73.6 against an estimated ceiling of 91.”

CRI authors (Nguyen, Cooper, Oesterheld, Kastner, Benton) with Anthropic, 14 August 2026

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

Read the story →

Receipts pack

The evidence file for this verdict

6 receipts: 1 support the claim, 1 contradict it, 4 add context. 3 figures on the record, 3 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 claimalignment.anthropic.com ↗

    Overall, this leads us to estimate ceiling performance on the CRI to be around 91. The highest-scoring model, Opus 5, is still well below this ceiling, with a score of 73.6 (95% CI: ± 2.1).

    Look up an archived copy ↗

  2. 2Contextalignment.anthropic.com ↗

    We measure how good models are at judging arguments against position texts by comparing their ratings to ours. Ratings follow a detailed rubric.

    Look up an archived copy ↗

  3. 3Contextalignment.anthropic.com ↗

    researcher Emery Cooper, and some were independently rated by at least one other researcher, for a total of 2,140 ratings

    Look up an archived copy ↗

  4. 4Contextalignment.anthropic.com ↗

    This work was done in collaboration with Anthropic.

    Look up an archived copy ↗

  5. 5Contradicts the claimnews.ycombinator.com ↗

    A closed source benchmark that Anthropic paid for that Anthropic ranked highest.

    Look up an archived copy ↗

  6. 6Contextbitcoinethereumnews.com ↗

    can't be checked against a clear right answer

    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.

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.