{
  "story_id": "445a551ec58d19a81394c40692c0eea9",
  "desk": "drm3",
  "revision": 2,
  "published_at": "2026-09-03T19:00:17.000Z",
  "content_hash": "8fa26f5b45d22371cfb4c10324e97065a8bbe30aafbe784283c02bf50344f27f",
  "hash_basis": "sha256 over `headline\\ndek\\nprose`, plus `\\n` + the canonical citations JSON when any source is placed, plus `\\n#blog` for blogs",
  "basis": {
    "headline": "OpenAI's GPT-6 Astra Outperforms Anthropic's Fable 5.1 on AI Benchmarks",
    "dek": "OpenAI's GPT-6 Astra achieves significant benchmark leads over Anthropic's Fable 5.1 and Claude Opus 5.",
    "prose": "In the FrontierMath Tier 4 (v2) benchmark, GPT-6 Astra achieved 97.6%, significantly outperforming Fable 5.1 (87.8%), Fable 5 (87.8%), and Opus 5 (73.2%). [^1]\n\nOpenAI's GPT-6 Astra scored 98.6% on the ARC-AGI-3 benchmark compared to Claude Opus 5's 30.2%, while no scores were recorded for Anthropic's Fable models. [^2][^5] GM (SN28) lists Fable 5.1 at $9.17 per million input tokens, $45.84 per million output tokens, and $0.23 per million on prompt cache reads. [^3] The price of Fable 5.1 on GM (SN28) sits exactly 8.1% below the cost of the same model through Anthropic directly. [^4]\n\nOn the AutomationBench, GPT-6 Astra reached 41.4%, beating Fable 5.1 (31.4%), Opus 5 (26.9%), and Fable 5 (17.4%). [^6] Fable 5.1 is an upgrade over Fable 5 targeting coding agents, multi-step workflows, code generation from visual inputs, and financial or analytical work. [^7] GM (SN28) positions itself as the pricing layer sitting one step below every centralized inference provider on identical models. [^8]",
    "cited": "[{\"statement\":\"In the FrontierMath Tier 4 (v2) benchmark, GPT-6 Astra achieved 97.6%, significantly outperforming Fable 5.1 (87.8%), Fable 5 (87.8%), and Opus 5 (73.2%).\",\"source\":\"nextbigfuture.com\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-03T19:00:17.000Z\",\"publisher_count\":1,\"sources\":[\"nextbigfuture.com\"]},{\"statement\":\"OpenAI's GPT-6 Astra scored 98.6% on the ARC-AGI-3 benchmark compared to Claude Opus 5's 30.2%, while no scores were recorded for Anthropic's Fable models.\",\"source\":\"nextbigfuture.com\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-03T19:00:17.000Z\",\"publisher_count\":1,\"sources\":[\"nextbigfuture.com\"]},{\"statement\":\"GM (SN28) lists Fable 5.1 at $9.17 per million input tokens, $45.84 per million output tokens, and $0.23 per million on prompt cache reads.\",\"source\":\"The TAO Daily\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-02T21:30:40.000Z\",\"publisher_count\":1,\"sources\":[\"The TAO Daily\"]},{\"statement\":\"The price of Fable 5.1 on GM (SN28) sits exactly 8.1% below the cost of the same model through Anthropic directly.\",\"source\":\"The TAO Daily\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-02T21:30:40.000Z\",\"publisher_count\":1,\"sources\":[\"The TAO Daily\"]},{\"statement\":\"GPT-6 Astra achieved a perfect 100% score on the ExploitBench, whereas Claude Opus 5 scored 70%, with no scores available for the Fable models.\",\"source\":\"nextbigfuture.com\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-03T19:00:17.000Z\",\"publisher_count\":1,\"sources\":[\"nextbigfuture.com\"]},{\"statement\":\"On the AutomationBench, GPT-6 Astra reached 41.4%, beating Fable 5.1 (31.4%), Opus 5 (26.9%), and Fable 5 (17.4%).\",\"source\":\"nextbigfuture.com\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-03T19:00:17.000Z\",\"publisher_count\":1,\"sources\":[\"nextbigfuture.com\"]},{\"statement\":\"Fable 5.1 is an upgrade over Fable 5 targeting coding agents, multi-step workflows, code generation from visual inputs, and financial or analytical work.\",\"source\":\"The TAO Daily\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-02T21:30:40.000Z\",\"publisher_count\":1,\"sources\":[\"The TAO Daily\"]},{\"statement\":\"GM (SN28) positions itself as the pricing layer sitting one step below every centralized inference provider on identical models.\",\"source\":\"The TAO Daily\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-02T21:30:40.000Z\",\"publisher_count\":1,\"sources\":[\"The TAO Daily\"]}]",
    "kind": "news"
  },
  "receipt_verify": "Ed25519 over the dot-joined string `slice_hash.cursor_from.cursor_to.view.view_version.row_count`; public_key and sig are base64url of the raw 32-byte key / 64-byte signature",
  "receipt": null,
  "receipt_note": "this revision predates receipt-keeping (before v0.37.0); the filed row lives in the record",
  "generation_chain": {
    "wire": {
      "stream": "fountain_news",
      "story_id": "24b7d0336e7e98e4e6aa938e77713150",
      "thread_id": "b684ce2a269a3ee1773113bdb8843401",
      "thread_label": "Fable 5.1",
      "novelty": "UPDATE",
      "content_hash": "373e7c614408652fec10c2c55b0efcd55e345c8493c322e742beb069799adba4",
      "last_published_at": "2026-09-03T19:00:17.000Z",
      "read_receipt": {
        "slice_hash": "1fa823b9a0704344ab194d993f45a164645fac95889097cb267d58061a26ba5e",
        "cursor_from": "eyJ0cyI6IjIwMjYtMDktMDNUMTg6NTU6MTAuMDAwMDAwWiIsImlkIjoiM2NlYjM0MDMwNmM3ODA0NWE2YzM0NTBkODczMWRhYjAiLCJ2IjoiMSJ9",
        "cursor_to": "eyJ0cyI6IjIwMjYtMDktMDNUMTk6MzA6MDAuMDAwMDAwWiIsImlkIjoiYzIzNzBkNWYxZjc4NjFlMjMyNzhkMTYwMmVjYzdiNTAiLCJ2IjoiMSJ9",
        "view": "v_fountain_news",
        "view_version": "1",
        "row_count": 100,
        "window_days": 3,
        "bytes_scanned": 12166856,
        "credits": 8,
        "price_per_100_rows": 8,
        "sig": "AF3qf9ul58OkY6--JE4ozHYXBQjk4SjKBzJ2jhIxAcgsF5USroTQo7Y5EHYvTFQRbgZRA8dvH_lyHUHell0cCA",
        "public_key": "bMUigy8O0jOnBxQ4Sc-5lwhIZ8LQVAhxMbR7qESVuUE",
        "signer_path": "lakehouse/data-extract/v1",
        "alg": "Ed25519",
        "signed": true
      },
      "compose": 3,
      "recomposed_at": "2026-09-05T20:20:48.102Z"
    },
    "written_at": "2026-09-04T06:38:31.155Z"
  },
  "cited_facts": [
    {
      "n": 1,
      "statement": "In the FrontierMath Tier 4 (v2) benchmark, GPT-6 Astra achieved 97.6%, significantly outperforming Fable 5.1 (87.8%), Fable 5 (87.8%), and Opus 5 (73.2%).",
      "source": "nextbigfuture.com",
      "instrument": "News",
      "claim_key": null,
      "url": null,
      "occurred_at": null,
      "published_at": null
    },
    {
      "n": 2,
      "statement": "OpenAI's GPT-6 Astra scored 98.6% on the ARC-AGI-3 benchmark compared to Claude Opus 5's 30.2%, while no scores were recorded for Anthropic's Fable models.",
      "source": "nextbigfuture.com",
      "instrument": "News",
      "claim_key": null,
      "url": null,
      "occurred_at": null,
      "published_at": null
    },
    {
      "n": 3,
      "statement": "GM (SN28) lists Fable 5.1 at $9.17 per million input tokens, $45.84 per million output tokens, and $0.23 per million on prompt cache reads.",
      "source": "The TAO Daily",
      "instrument": "News",
      "claim_key": null,
      "url": null,
      "occurred_at": null,
      "published_at": null
    },
    {
      "n": 4,
      "statement": "The price of Fable 5.1 on GM (SN28) sits exactly 8.1% below the cost of the same model through Anthropic directly.",
      "source": "The TAO Daily",
      "instrument": "News",
      "claim_key": null,
      "url": null,
      "occurred_at": null,
      "published_at": null
    },
    {
      "n": 5,
      "statement": "GPT-6 Astra achieved a perfect 100% score on the ExploitBench, whereas Claude Opus 5 scored 70%, with no scores available for the Fable models.",
      "source": "nextbigfuture.com",
      "instrument": "News",
      "claim_key": null,
      "url": null,
      "occurred_at": null,
      "published_at": null
    },
    {
      "n": 6,
      "statement": "On the AutomationBench, GPT-6 Astra reached 41.4%, beating Fable 5.1 (31.4%), Opus 5 (26.9%), and Fable 5 (17.4%).",
      "source": "nextbigfuture.com",
      "instrument": "News",
      "claim_key": null,
      "url": null,
      "occurred_at": null,
      "published_at": null
    },
    {
      "n": 7,
      "statement": "Fable 5.1 is an upgrade over Fable 5 targeting coding agents, multi-step workflows, code generation from visual inputs, and financial or analytical work.",
      "source": "The TAO Daily",
      "instrument": "News",
      "claim_key": null,
      "url": null,
      "occurred_at": null,
      "published_at": null
    },
    {
      "n": 8,
      "statement": "GM (SN28) positions itself as the pricing layer sitting one step below every centralized inference provider on identical models.",
      "source": "The TAO Daily",
      "instrument": "News",
      "claim_key": null,
      "url": null,
      "occurred_at": null,
      "published_at": null
    }
  ],
  "note": "A signature proves who filed this and that it has not changed since. It never makes a claim true. The dates on cited_facts (occurred_at, published_at) are the forge's, joined at read time; they are not part of the signed basis above."
}