MLE-bench

Données structurées de l’entrée pour les outils humains, les systèmes IA et les clients machine.

{
    "@context": [
        "https://schema.org",
        {
            "lxw": "https://lxkeys.world/schema/"
        }
    ],
    "@type": "Thing",
    "identifier": "ENT-00001968",
    "name": "MLE-bench",
    "alternateName": [],
    "additionalType": {
        "category": "Data and Evaluation",
        "type": "Benchmark",
        "subtype": "",
        "lxkeysEntity": false
    },
    "description": "MLE-bench is a AI benchmark associated with OpenAI, classified in LXKeys.world as AI Benchmark / Evaluation.",
    "creator": "OpenAI",
    "url": "https://lxkeys.world/entry.php?id=ENT-00001968&lang=fr",
    "sameAs": "https://github.com/openai/mle-bench",
    "image": "",
    "lxkeysWorld": {
        "worldId": "ENT-00001968",
        "kind": "Data and Evaluation",
        "type": "Benchmark",
        "subtype": "",
        "classification": "AI Benchmark / Evaluation",
        "organization": "OpenAI",
        "originContext": "Public AI and technical record",
        "firstPublicAppearance": "2024",
        "currentStatus": "Active",
        "documentationStatus": "Documented",
        "documentationIndex": {
            "total": 74,
            "documentation": 25,
            "evidence": 13,
            "structure": 25,
            "relationships": 11,
            "level": "Level IV Connected"
        },
        "lxCalendarium": {
            "start_date_utc": "2023-04-01",
            "created_utc": "2026-06-16T23:59:29+00:00",
            "created_dypclt": "D-0 Y-2 P-3 C-3 L-21 T-3",
            "updated_utc": "2026-06-16T23:59:29+00:00",
            "updated_dypclt": "D-0 Y-2 P-3 C-3 L-21 T-3"
        },
        "facts": [],
        "capabilities": [
            "Documented source context",
            "Public reference anchor",
            "Structured classification"
        ],
        "limitations": [
            "Benchmark scores depend on the exact dataset version, prompt or evaluation protocol, scoring implementation and contamination controls.",
            "Leaderboard performance should not be treated as a complete measure of real-world capability or safety.",
            "Benchmark relevance can decline as models, data and evaluation practices evolve."
        ],
        "tags": [
            "Documented Entity",
            "AI System",
            "Registry Candidate"
        ],
        "timeline": [
            {
                "date": "2024",
                "title": "Initial benchmark release",
                "description": "MLE-bench entered the documented public record in 2024. This event is retained at the precision supported by the Entry’s reviewed source history.",
                "source_url": "https://github.com/openai/mle-bench",
                "verification_status": "source_backed_curated_baseline"
            }
        ],
        "relationships": [
            {
                "target": "OpenAI",
                "type": "Published by",
                "description": "MLE-bench is associated with OpenAI through its documented source context.",
                "evidence_level": "documentary",
                "target_id": "ENT-00000048"
            }
        ],
        "sources": [
            {
                "label": "MLE-bench repository",
                "url": "https://github.com/openai/mle-bench",
                "source_type": "Official Repository",
                "verification_status": "verified",
                "authority": "TRUSTED_PRIMARY",
                "role": "code_repository",
                "update_enabled": false,
                "authority_basis": "curated-corpus-refresh-2026-09-08"
            }
        ],
        "canonical": [],
        "imageMeta": []
    }
}