{
  "schema_version": "1.1",
  "id": "auto-cc8e132c61",
  "slug": "how-enabling-two-settings-tripled-our-scores-on-the-arc--cc8e132c61",
  "url": "https://feed7.dev/p/how-enabling-two-settings-tripled-our-scores-on-the-arc--cc8e132c61",
  "title": "How enabling two settings tripled our scores on the ARC-AGI-3 benchmark",
  "why_included": "Record reasoning retention and compaction with the model name because runtime settings can materially alter agent eval results.",
  "summary": "Two API settings—reasoning retention and compaction—reportedly tripled GPT-5.6’s ARC-AGI-3 score. Agent evals should treat runtime configuration as part of the tested system.",
  "practical_implication": "Record these settings alongside the model name in agent evaluations. Configuration can materially affect results, so defaults and explicit settings should not be compared as equivalent systems.",
  "agent_context": "OpenAI says enabling **reasoning retention** and **compaction** produced **3× ARC-AGI-3 scores** for GPT-5.6 while also improving efficiency.\n\nRecord these settings alongside the model name in agent evaluations. Configuration can materially affect results, so defaults and explicit settings should not be compared as equivalent systems.\n\nThe supplied material provides no absolute scores, token usage, latency, or experimental detail, leaving the size and generality of the efficiency gain unclear.",
  "source": {
    "name": "OpenAI",
    "url": "https://openai.com/index/how-two-settings-tripled-our-arc-agi-3-scores",
    "published_at": "2026-07-29T00:00:00.000Z"
  },
  "source_class": "blog_post",
  "content_type": "Official Release",
  "layer": "benchmark",
  "domains": [],
  "topics": [
    "agent-evals",
    "benchmark-integrity",
    "context-caching"
  ],
  "verification": {
    "status": "official_source",
    "label": "Official Source",
    "method": "source_feed",
    "verified_at": null
  },
  "uncertainty": [],
  "connected_context": null,
  "lifecycle": "New",
  "published_at": "2026-07-29T00:00:00.000Z",
  "modified_at": "2026-07-29T00:00:00.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/how-enabling-two-settings-tripled-our-scores-on-the-arc--cc8e132c61",
    "json": "https://feed7.dev/p/how-enabling-two-settings-tripled-our-scores-on-the-arc--cc8e132c61.json",
    "markdown": "https://feed7.dev/p/how-enabling-two-settings-tripled-our-scores-on-the-arc--cc8e132c61.md"
  }
}