BEHAVIOR Benchmark

Structured entry data for human tools, AI systems and machine clients.

{
    "@context": [
        "https://schema.org",
        {
            "lxw": "https://lxkeys.world/schema/"
        }
    ],
    "@type": "Thing",
    "identifier": "ENT-00002680",
    "name": "BEHAVIOR Benchmark",
    "alternateName": [],
    "additionalType": {
        "category": "Data and Evaluation",
        "type": "Benchmark",
        "subtype": "",
        "lxkeysEntity": false
    },
    "description": "BEHAVIOR Benchmark is a AI benchmark associated with Stanford University, classified in LXKeys.world as AI Benchmark / Evaluation.",
    "creator": "Stanford University",
    "url": "https://lxkeys.world/entry.php?id=ENT-00002680&lang=en",
    "sameAs": "https://behavior.stanford.edu/",
    "image": "",
    "lxkeysWorld": {
        "worldId": "ENT-00002680",
        "kind": "Data and Evaluation",
        "type": "Benchmark",
        "subtype": "",
        "classification": "AI Benchmark / Evaluation",
        "organization": "Stanford University",
        "originContext": "AI evaluation",
        "firstPublicAppearance": "2021",
        "currentStatus": "Active",
        "documentationStatus": "Documented",
        "documentationIndex": {
            "total": 82,
            "documentation": 25,
            "evidence": 13,
            "structure": 25,
            "relationships": 19,
            "level": "Level V Persistent"
        },
        "lxCalendarium": {
            "start_date_utc": "2023-04-01",
            "created_utc": "2026-06-17T01:48:33+00:00",
            "created_dypclt": "D-0 Y-2 P-3 C-3 L-22 T-4",
            "updated_utc": "2026-06-17T01:48:33+00:00",
            "updated_dypclt": "D-0 Y-2 P-3 C-3 L-22 T-4"
        },
        "facts": [],
        "capabilities": [
            "Evaluation protocol documentation",
            "Model comparison support",
            "Task taxonomy mapping",
            "Reproducible benchmark anchoring",
            "Relationship graph compatibility"
        ],
        "limitations": [
            "Benchmark results can become stale as models improve and evaluation protocols evolve.",
            "A benchmark measures a defined task scope rather than complete intelligence."
        ],
        "tags": [
            "Benchmark",
            "Evaluation",
            "AI Safety",
            "Agent Evaluation"
        ],
        "timeline": [
            {
                "date": "2021",
                "title": "Initial benchmark release",
                "description": "BEHAVIOR Benchmark entered the documented public record in 2021. This event is retained at the precision supported by the Entry’s reviewed source history.",
                "source_url": "https://behavior.stanford.edu/",
                "verification_status": "source_backed_official"
            }
        ],
        "relationships": [
            {
                "target": "Stanford University",
                "type": "Associated organization",
                "description": "Stanford University is the organization, project community or institutional context associated with BEHAVIOR Benchmark.",
                "evidence_level": "documentary"
            },
            {
                "target": "AI evaluation",
                "type": "Domain context",
                "description": "BEHAVIOR Benchmark belongs to the AI evaluation layer of the intelligent-entity registry.",
                "evidence_level": "documentary"
            }
        ],
        "sources": [
            {
                "label": "Official documentation",
                "url": "https://behavior.stanford.edu/",
                "source_type": "Official / Research Source",
                "verification_status": "verified",
                "authority": "OFFICIAL",
                "role": "primary",
                "update_enabled": true,
                "authority_basis": "curated-corpus-refresh-2026-09-08"
            }
        ],
        "canonical": [],
        "imageMeta": []
    }
}