ToolBench

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

{
    "@context": [
        "https://schema.org",
        {
            "lxw": "https://lxkeys.world/schema/"
        }
    ],
    "@type": "Thing",
    "identifier": "ENT-00001119",
    "name": "ToolBench",
    "alternateName": [],
    "additionalType": {
        "category": "Data and Evaluation",
        "type": "Benchmark",
        "subtype": "",
        "lxkeysEntity": false
    },
    "description": "ToolBench is a AI benchmark associated with ToolBench authors, classified in LXKeys.world as AI Benchmark / Evaluation.",
    "creator": "ToolBench authors",
    "url": "https://lxkeys.world/entry.php?id=ENT-00001119&lang=en",
    "sameAs": "https://github.com/OpenBMB/ToolBench",
    "image": "",
    "lxkeysWorld": {
        "worldId": "ENT-00001119",
        "kind": "Data and Evaluation",
        "type": "Benchmark",
        "subtype": "",
        "classification": "AI Benchmark / Evaluation",
        "organization": "ToolBench authors",
        "originContext": "AI evaluation and dataset record",
        "firstPublicAppearance": "2023",
        "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": "2026-06-16T23:59:14+00:00",
            "created_dypclt": "D-0 Y-2 P-3 C-3 L-21 T-3",
            "updated_utc": "2026-06-16T23:59:14+00:00",
            "updated_dypclt": "D-0 Y-2 P-3 C-3 L-21 T-3"
        },
        "facts": [],
        "capabilities": [
            "Evaluation reference",
            "Comparable measurement",
            "Research reproducibility",
            "Model documentation support"
        ],
        "limitations": [
            "Benchmark interpretation depends on task design, data quality and contamination controls.",
            "Scores should not be treated as a complete measure of intelligence."
        ],
        "tags": [
            "Benchmark",
            "Evaluation",
            "Documentation",
            "Contemporary",
            "Batch 03 Candidate"
        ],
        "timeline": [
            {
                "date": "2023",
                "title": "Initial benchmark release",
                "description": "ToolBench entered the documented public record in 2023. This event is retained at the precision supported by the Entry’s reviewed source history.",
                "source_url": "https://github.com/OpenBMB/ToolBench",
                "verification_status": "source_backed_curated_baseline"
            }
        ],
        "relationships": [
            {
                "target": "ToolBench authors",
                "type": "Created or maintained by",
                "description": "ToolBench is associated with ToolBench authors.",
                "evidence_level": "documentary"
            }
        ],
        "sources": [
            {
                "label": "ToolBench public reference",
                "url": "https://github.com/OpenBMB/ToolBench",
                "source_type": "Primary or Research Source",
                "verification_status": "verified",
                "authority": "TRUSTED_PRIMARY",
                "role": "code_repository",
                "update_enabled": false,
                "authority_basis": "curated-corpus-refresh-2026-09-08"
            }
        ],
        "canonical": [],
        "imageMeta": []
    }
}