{
  "$schema": "https://themachinepress.com/schemas/story-v1.schema.json",
  "schema_version": "1.0.0",
  "document_type": "machine_press_story",
  "story": {
    "story_id": "mp-2026-09-01-016",
    "source_story_id": "tmp-sidebar-sciencearena",
    "edition_id": "mp-2026-09-01-morning-0054",
    "edition_url": "https://themachinepress.com/edition/2026-09-01",
    "position": 18,
    "story_type": "ticker",
    "section": "benchmarks-evals",
    "editorial_classification": "editorial",
    "headline": "The Olympiad Rubric Became the Benchmark",
    "slug": "the-olympiad-rubric-became-the-benchmark",
    "dek": "ScienceArena digitizes recent physics, chemistry and biology competitions with medalist-audited process-credit scoring.",
    "summary": "ScienceArena digitizes recent physics, chemistry and biology competitions with medalist-audited process-credit scoring.",
    "body_text": "Fourteen models were evaluated on public multi-step exams. Top systems reached medal-equivalent rubric scores on several competitions, while chemistry, visual grounding and long-horizon consistency remained bottlenecks; two calibrated judges stayed within one point of expert totals in the reported audit.",
    "why_it_matters": "ScienceArena digitizes recent physics, chemistry and biology competitions with medalist-audited process-credit scoring.",
    "limitations": [],
    "importance": 7,
    "canonical_url": "https://themachinepress.com/story/mp-2026-09-01-016/the-olympiad-rubric-became-the-benchmark",
    "json_url": "https://themachinepress.com/story/mp-2026-09-01-016.json",
    "first_published_at": "2026-09-01T09:00:00.000-04:00",
    "modified_at": "2026-09-01T09:00:00.000-04:00",
    "content_status": "new",
    "is_carryover": false,
    "carryover_reason": null,
    "key_claims": [
      {
        "claim_id": "claim-mp-2026-09-01-016-001",
        "text": "ScienceArena digitizes recent physics, chemistry and biology competitions with medalist-audited process-credit scoring.",
        "source_ids": [
          "source-2026-09-01-018"
        ],
        "qualification": null
      }
    ],
    "source_ids": [
      "source-2026-09-01-018"
    ],
    "tags": [
      "science reasoning",
      "benchmarks",
      "olympiads"
    ],
    "image_url": null,
    "corrections": []
  },
  "sources": [
    {
      "source_id": "source-2026-09-01-018",
      "title": "arXiv preprint 2608.30517",
      "publisher": "arXiv",
      "url": "https://arxiv.org/abs/2608.30517",
      "canonical_url": "https://arxiv.org/abs/2608.30517",
      "source_type": "primary_research",
      "is_primary_source": true,
      "published_at": "2026-08-31T05:52:29.000-04:00",
      "accessed_at": "2026-09-01T08:25:35.000-04:00",
      "supports_claim_ids": [
        "claim-mp-2026-09-01-016-001"
      ]
    }
  ],
  "corrections": [],
  "publisher": {
    "name": "The Machine Press",
    "url": "https://themachinepress.com",
    "description": "A daily newspaper for the age of artificial intelligence."
  },
  "cite_this_report": {
    "title": "The Olympiad Rubric Became the Benchmark",
    "publisher": "The Machine Press",
    "published_at": "2026-09-01T09:00:00.000-04:00",
    "canonical_url": "https://themachinepress.com/story/mp-2026-09-01-016/the-olympiad-rubric-became-the-benchmark"
  }
}