Start free trial

TRUE, BUTCherry-Picked Slice

Tied with GPT-6 Astra on the index

The independent index has it tied with GPT-6 Astra and five points behind Claude Opus 5.5.

“Google's Gemini 4 Argon scored significantly higher than OpenAI's GPT-6 Astra and Anthropic's Fable and Opus models across a variety of AI benchmarks.”

Google, Gemini 4 Argon launch post, 30 September 2026

Recorded 1 October 2026. Our ruling means: literally true, materially misleading.

Read the story →

Receipts pack

The evidence file for this verdict

12 receipts: 3 support the claim, 2 contradict it, 7 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 claimtechcrunch.com ↗

    Google claims that Argon scored significantly higher than OpenAI’s GPT-6 Astra and Anthropic’s Fable and Opus models across a variety of AI benchmarks.

    Look up an archived copy ↗

  2. 2Supports the claimblog.google ↗

    It sets a new state of the art on DeepSWE v1.1 (77.9%), which measures a model’s performance in real-world long-horizon software engineering tasks.

    Look up an archived copy ↗

  3. 3Supports the claimblog.google ↗

    Argon ties for first place with a top score of 68%

    Look up an archived copy ↗

  4. 4Contexttechcrunch.com ↗

    to show that Argon is currently the leading model on the company’s AI model index.

    Look up an archived copy ↗

  5. 5Contradicts the claimartificialanalysis.ai ↗

    scores 53 on the Artificial Analysis Intelligence Index, matching GPT-6 Astra (max, 53)

    Look up an archived copy ↗

  6. 6Contradicts the claimthe-decoder.com ↗

    Anthropic's models still lead. Claude Opus 5.5 sits at 58 points and Claude Sonnet 5.5 at 56.

    Look up an archived copy ↗

  7. 7Contextthe-decoder.com ↗

    Google's own benchmark results paint a rosier picture. Argon leads in most of those benchmarks, sometimes by wide margins.

    Look up an archived copy ↗

  8. 8Contextartificialanalysis.ai ↗

    averaging 62k output tokens per task, compared with 27k for GPT-6 Astra (max)

    Look up an archived copy ↗

  9. 9Contextblog.google ↗

    After the introductory period expires, the price of $4 per 1M input tokens and $20 per 1M output tokens will apply.

    Look up an archived copy ↗

  10. 10Contextartificialanalysis.ai ↗

    costs $1.99 per Intelligence Index task, 60% of GPT-6 Astra (max, $3.26)

    Look up an archived copy ↗

  11. 11Contexttechcrunch.com ↗

    being rolled out to a select group of the company’s cyber partners through its Fairwind Program

    Look up an archived copy ↗

  12. 12Contextthe-decoder.com ↗

    The price advantage comes from lower token rates, not from efficiency.

    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.