{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.05497", "kind": "paper", "url": "https://arxiv.org/abs/2606.05497"}], "authors": ["Alvin Wei Ming Tan", "David Cardinal", "Tania Lorido-Botran", "Laura Bravo-Sanchez", "Sunny Yu", "Michael C. Frank"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.05497", "source_url": "https://arxiv.org/abs/2606.05497"}, "categories": ["General AI", "Language & Knowledge", "cs.LG"], "description": {"en": "LEVANTE-bench evaluates vision-language models on six cognitive tasks from the LEVANTE dataset, comparing model performance and error patterns with children aged 5-12 across three countries."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.05497", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.05497", "title": "LEVANTE-bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Stanford University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.05497", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.05497", "source_url": "https://openalex.org/W7163691791"}, "key": "claire-radar:2606.05497", "modality": null, "name": "LEVANTE-bench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "unknown", "origin_record_id": "bm_levante-bench_b9930c93", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "cbef44ab053291cbd78d458b6407db7652a2842139dc5e556dd32717ea9cbef2", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.05497"}, "publisher": null, "released": "2026-06-03", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.05497", "source_url": "https://arxiv.org/abs/2606.05497"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-05497", "source": "claire_radar", "source_benchmark_id": "2606.05497", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2606.05497", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "unavailable"}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "488d9807d6565ff19365194f5250dd2a46907f4353fb98eb5190f3f7e78c03a3", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "LEVANTE-bench evaluates vision-language models on six cognitive tasks from the LEVANTE dataset, comparing model performance and error patterns with children aged 5-12 across three countries.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We present LEVANTE-bench, a benchmark based on tasks and data from the Learning Variability Network (LEVANTE), which distributes open-source tasks and data measuring children's cognition across languages and cultures."}, "familyId": "bmf_4b5b1a7a3878", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_levante-bench_b9930c93", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.05497", "paper": "https://arxiv.org/abs/2606.05497", "pdf": "https://arxiv.org/pdf/2606.05497", "project": null, "report": "https://arxiv.org/abs/2606.05497"}, "metrics": [], "motivation": "Given the inherently multimodal nature of human experience, vision-language models (VLMs) hold substantial promise for modeling human cognition as it grows and develops with experience.", "name": "LEVANTE-bench", "oneLine": "LEVANTE-bench evaluates vision-language models on six cognitive tasks from the LEVANTE dataset, comparing model performance and error patterns with children aged 5-12 across three countries.", "paperTitle": "LEVANTE-bench: Multi-Scale Comparison of VLMs to Children Using Cognitive Tasks (or, \"Is Your VLM Smarter Than a 5th Grader?\")", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.05497", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "LEVANTE-bench Authors", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2606.05497"}], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-03", "source": {"authors": ["Alvin Wei Ming Tan", "David Cardinal", "Tania Lorido-Botran", "Laura Bravo-Sanchez", "Sunny Yu and Michael C. Frank"], "categories": ["cs.LG"], "id": "2606.05497", "title": "LEVANTE-bench: Multi-Scale Comparison of VLMs to Children Using Cognitive Tasks (or, \"Is Your VLM Smarter Than a 5th Grader?\")", "type": "arxiv", "url": "https://arxiv.org/abs/2606.05497"}, "sourceUpdatedAt": "2026-06-03T22:41:11Z", "topics": ["cs.LG"], "venueAttempts": [], "whyItMatters": "LEVANTE-bench addresses the gap in evaluating VLMs against human cognitive development, providing a structured comparison that can inform model design and understanding of alignment with human cognition."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
