ForecastBench

{
  "id": "forecastbench",
  "numericId": null,
  "path": "/knowledge-base/responses/forecastbench/",
  "filePath": "knowledge-base/responses/forecastbench.mdx",
  "title": "ForecastBench",
  "quality": 53,
  "readerImportance": 20,
  "researchImportance": 32.5,
  "tacticalValue": null,
  "contentFormat": "article",
  "tractability": null,
  "neglectedness": null,
  "uncertainty": null,
  "causalLevel": null,
  "lastUpdated": "2026-03-13",
  "dateCreated": "2026-02-15",
  "llmSummary": "ForecastBench is a dynamic, contamination-free benchmark with 1,000 continuously-updated questions comparing LLM forecasting to superforecasters. GPT-4.5 achieves 0.101 Brier score vs 0.081 for superforecasters; linear extrapolation projects LLMs will match human experts by November 2026 (95% CI: Dec 2025 – Jan 2028).",
  "description": "A dynamic, contamination-free benchmark for evaluating large language model forecasting capabilities, published at ICLR 2025. With 1,000 continuously-updated questions about future events, ForecastBench compares LLMs to superforecasters and finds GPT-4.5 (Feb 2025) achieves 0.101 difficulty-adjusted Brier score vs 0.081 for superforecasters—linear extrapolation suggests LLMs will match human superforecasters by November 2026 (95% CI: December 2025 – January 2028).",
  "ratings": {
    "novelty": 5,
    "rigor": 6.5,
    "actionability": 4.5,
    "completeness": 7
  },
  "category": "responses",
  "subcategory": "epistemic-platforms",
  "clusters": [
    "epistemics",
    "ai-safety"
  ],
  "metrics": {
    "wordCount": 1899,
    "tableCount": 21,
    "diagramCount": 1,
    "internalLinks": 12,
    "externalLinks": 11,
    "footnoteCount": 0,
    "bulletRatio": 0.05,
    "sectionCount": 31,
    "hasOverview": true,
    "structuralScore": 15
  },
  "suggestedQuality": 100,
  "updateFrequency": 45,
  "evergreen": true,
  "wordCount": 1899,
  "unconvertedLinks": [
    {
      "text": "FRI Project Page",
      "url": "https://forecastingresearch.org/",
      "resourceId": "46c32aeaf3c3caac",
      "resourceTitle": "Forecasting Research Institute"
    }
  ],
  "unconvertedLinkCount": 1,
  "convertedLinkCount": 0,
  "backlinkCount": 6,
  "hallucinationRisk": {
    "level": "medium",
    "score": 55,
    "factors": [
      "no-citations"
    ]
  },
  "entityType": "project",
  "redundancy": {
    "maxSimilarity": 16,
    "similarPages": [
      {
        "id": "ai-forecasting-benchmark",
        "title": "AI Forecasting Benchmark Tournament",
        "path": "/knowledge-base/responses/ai-forecasting-benchmark/",
        "similarity": 16
      },
      {
        "id": "fri",
        "title": "Forecasting Research Institute",
        "path": "/knowledge-base/organizations/fri/",
        "similarity": 12
      },
      {
        "id": "metaforecast",
        "title": "Metaforecast",
        "path": "/knowledge-base/responses/metaforecast/",
        "similarity": 11
      },
      {
        "id": "squiggleai",
        "title": "SquiggleAI",
        "path": "/knowledge-base/responses/squiggleai/",
        "similarity": 11
      },
      {
        "id": "xpt",
        "title": "XPT (Existential Risk Persuasion Tournament)",
        "path": "/knowledge-base/responses/xpt/",
        "similarity": 11
      }
    ]
  },
  "coverage": {
    "passing": 7,
    "total": 13,
    "targets": {
      "tables": 8,
      "diagrams": 1,
      "internalLinks": 15,
      "externalLinks": 9,
      "footnotes": 6,
      "references": 6
    },
    "actuals": {
      "tables": 21,
      "diagrams": 1,
      "internalLinks": 12,
      "externalLinks": 11,
      "footnotes": 0,
      "references": 1,
      "quotesWithQuotes": 0,
      "quotesTotal": 0,
      "accuracyChecked": 0,
      "accuracyTotal": 0
    },
    "items": {
      "llmSummary": "green",
      "schedule": "green",
      "entity": "green",
      "editHistory": "red",
      "overview": "green",
      "tables": "green",
      "diagrams": "green",
      "internalLinks": "amber",
      "externalLinks": "green",
      "footnotes": "red",
      "references": "amber",
      "quotes": "red",
      "accuracy": "red"
    },
    "ratingsString": "N:5 R:6.5 A:4.5 C:7"
  },
  "readerRank": 521,
  "researchRank": 398,
  "recommendedScore": 137.61
}

No external links