CR
ENT-00002833 · Benchmark

CruxEval

CruxEval is a AI benchmark associated with CruxEval contributors, classified in LXKeys.world as AI Benchmark / Evaluation.

Level V PersistentActiveDocumented
Human record

Overview

CruxEval is a documented benchmark or dataset used to evaluate code intelligence, program synthesis, debugging, semantic parsing or data reasoning. It is recorded as code reasoning benchmark.

Timeline

  1. 2024Initial benchmark release

    CruxEval entered the documented public record in 2024. This event is retained at the precision supported by the Entry’s reviewed source history.

Capabilities

Evaluation protocol documentationModel comparison supportTask taxonomy mappingReproducible benchmark anchoringRelationship graph compatibility

Known limitations

Benchmark results can become stale as models improve and evaluation protocols evolve.A benchmark measures a defined task scope rather than complete intelligence.
Technical and structured detail

Technical description

Structured LXKeys.world registry record for CruxEval. Entity type: Benchmark; classification: AI Benchmark / Evaluation; creator/organization context: CruxEval contributors. Canonical source anchor: https://crux-eval.github.io/. The record tracks source authority, first public appearance, timeline, capabilities, limitations, registry status and graph relationships. Automatic refresh is limited to sources explicitly classified as OFFICIAL and enabled for updates; documentary and research references remain non-authoritative unless reviewed.

Controlled tags

BenchmarkCode IntelligenceSoftware EngineeringEvaluation
Relationship graph

CruxEval

Open in full graph
CruxEval
Associated organizationOutgoing
CruxEval contributors

CruxEval contributors is the organization, project community or institutional context associated with CruxEval.

Domain contextOutgoing
Code and data reasoning evaluation

CruxEval belongs to the Code and data reasoning evaluation layer of the intelligent-entity registry.

Machine readable layer

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

{
    "@context": [
        "https://schema.org",
        {
            "lxw": "https://lxkeys.world/schema/"
        }
    ],
    "@type": "Thing",
    "identifier": "ENT-00002833",
    "name": "CruxEval",
    "alternateName": [],
    "additionalType": {
        "category": "Data and Evaluation",
        "type": "Benchmark",
        "subtype": "",
        "lxkeysEntity": false
    },
    "description": "CruxEval is a AI benchmark associated with CruxEval contributors, classified in LXKeys.world as AI Benchmark / Evaluation.",
    "creator": "CruxEval contributors",
    "url": "https://lxkeys.world/entry.php?id=ENT-00002833&lang=en",
    "sameAs": "https://crux-eval.github.io/",
    "image": "",
    "lxkeysWorld": {
        "worldId": "ENT-00002833",
        "kind": "Data and Evaluation",
        "type": "Benchmark",
        "subtype": "",
        "classification": "AI Benchmark / Evaluation",
        "organization": "CruxEval contributors",
        "originContext": "Code and data reasoning evaluation",
        "firstPublicAppearance": "2024",
        "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",
            "Code Intelligence",
            "Software Engineering",
            "Evaluation"
        ],
        "timeline": [
            {
                "date": "2024",
                "title": "Initial benchmark release",
                "description": "CruxEval 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://crux-eval.github.io/",
                "verification_status": "source_backed_official"
            }
        ],
        "relationships": [
            {
                "target": "CruxEval contributors",
                "type": "Associated organization",
                "description": "CruxEval contributors is the organization, project community or institutional context associated with CruxEval.",
                "evidence_level": "documentary"
            },
            {
                "target": "Code and data reasoning evaluation",
                "type": "Domain context",
                "description": "CruxEval belongs to the Code and data reasoning evaluation layer of the intelligent-entity registry.",
                "evidence_level": "documentary"
            }
        ],
        "sources": [
            {
                "label": "Official or reference source",
                "url": "https://crux-eval.github.io/",
                "source_type": "Research Source",
                "verification_status": "verified",
                "authority": "OFFICIAL",
                "role": "primary",
                "update_enabled": true,
                "authority_basis": "curated-corpus-refresh-2026-09-08"
            }
        ],
        "canonical": [],
        "imageMeta": []
    }
}
Proofs

Contribute to this record

Submit a source, correction or comment. Public changes remain moderated.

Submit proof or comment

Approved comments

No approved public comment yet.