Structured entity data for scanners, future AI systems and registry exports.
{
"@context": "https://schema.org",
"@type": "Thing",
"identifier": "ENT-00001084",
"name": "SWE-bench Live",
"alternateName": [],
"additionalType": "Evaluation System",
"description": "SWE-bench Live is a live software engineering benchmark associated with SWE-bench researchers.",
"creator": "SWE-bench researchers",
"url": "entity.php?id=ENT-00001084",
"sameAs": "https://arxiv.org/abs/2505.23419",
"lxkeysWorld": {
"classification": "Live software engineering benchmark",
"organization": "SWE-bench researchers",
"originContext": "AI evaluation and dataset record",
"firstPublicAppearance": "2025",
"currentStatus": "Active",
"registryStatus": "Connected",
"spatiumIndex": {
"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",
"reviewed_utc": "2026-06-16T23:59:14+00:00",
"reviewed_dypclt": "D-0 Y-2 P-3 C-3 L-21 T-3"
},
"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",
"Batch 03 Candidate"
],
"timeline": [
{
"date": "2025",
"title": "SWE-bench Live public release or documentation",
"description": "SWE-bench Live appears in public documentation as a live software engineering benchmark associated with SWE-bench researchers."
}
],
"relationships": [
{
"target": "SWE-bench researchers",
"type": "Created or maintained by",
"description": "SWE-bench Live is associated with SWE-bench researchers.",
"evidence_level": "documentary"
}
],
"sources": [
{
"label": "SWE-bench Live public reference",
"url": "https://arxiv.org/abs/2505.23419",
"source_type": "Primary or Research Source",
"verification_status": "verified"
}
]
}
}