Start free trial

TRUE, BUTCherry-Picked Slice

The sample size was ten questions.

“A viral claim on X said the mystery stealth model 'Ox Alpha' beats Claude Fable 5 and GPT-5.6 Sol on the DeepSWE coding benchmark, based on an 8/10-task sample (effectively >80%).”

Ben Davis, @davis7 on X, amplified by AGTP (@AGTPinsights) and Coin Bureau (@coinbureau) to a much larger audience without the sample-size caveat, 21 August 2026

Recorded 28 August 2026. Our ruling means: literally true, materially misleading.

Read the story →

Receipts pack

The evidence file for this verdict

7 receipts: 2 support the claim, 2 contradict it, 3 add context. 5 figures on the record, 4 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 claimx.com ↗

    gpt-5.6-sol: 52% fable: 65% whatever the hell this is: 80%

    Look up an archived copy ↗

  2. 2Contradicts the claimx.com ↗

    Actual DeepSWE run on the ox alpha mystery model is done. Ended at ~63% NOT the 80% my first subset test got

    Look up an archived copy ↗

  3. 3Contradicts the claimstealthmodelwatch.online ↗

    The rumored ~80% pass rate is completely incorrect

    Look up an archived copy ↗

  4. 4Contexttogether.ai ↗

    Sol edges ahead: 72.7% pass@1 to GLM-5.3's 69.0%

    Look up an archived copy ↗

  5. 5Supports the claimx.com ↗

    BREAKING: A mysterious new AI model called "Ox Alpha" is reportedly BEATING Claude Fable 5 and GPT-5.6 Sol at coding, and nobody knows who built it

    Look up an archived copy ↗

  6. 6Contextvktr.com ↗

    On August 26, Z.ai confirmed authorship of the model, vindicating the fingerprinting. The model's official name is GLM-5.3-Flash

    Look up an archived copy ↗

  7. 7Contexttogether.ai ↗

    It ties Sol at pass@2 (81.1 vs. 81.0) and leads pass@4 (87.6% vs. 85.8%)

    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.