{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.09548", "kind": "paper", "url": "https://arxiv.org/abs/2608.09548"}, {"id": "gh:zeroloss-lab/elbench", "kind": "repo", "url": "https://github.com/ZeroLoss-Lab/ELBench"}, {"id": "hf:zeroloss-lab/elbench", "kind": "dataset", "url": "https://huggingface.co/datasets/ZeroLoss-Lab/ELBench"}], "authors": ["Yilin Jiang", "Xiaorong Zhu", "Fei Tan", "Zicheng Zhang", "Kaiyi Huang", "Yang Yu", "Zexuan Fei", "Yiming Luo", "Keqian Li", "Hao Hao", "Guangtao Zhai", "Aimin Zhou"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.09548", "source_url": "https://arxiv.org/abs/2608.09548"}, "categories": ["General AI", "Safety", "Safety & Trustworthiness"], "description": {"en": "ELBench is a benchmark for education-facing large language models, evaluating General Capability, Safety and Trustworthiness, Basic Education, and High-Level Cultivation under a common protocol with 2,939 items."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.09548", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.09548", "title": "ELBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["The Hong Kong University of Science and Technology (Guangzhou)", "East China Normal University", "Shanghai Jiao Tong University", "Shanghai Artificial Intelligence Laboratory"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.09548", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.09548", "source_url": "https://openalex.org/W7202170841"}, "key": "claire-radar:2608.09548", "modality": null, "name": "ELBench", "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_elbench_6c33e0fa", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "5c5e408d68300b4ce9a79aa2399754696fd36eff74943ec1ea8b18909c2cd93f", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.09548"}, "publisher": null, "released": "2026-08-10", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.09548", "source_url": "https://arxiv.org/abs/2608.09548"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-09548", "source": "claire_radar", "source_benchmark_id": "2608.09548", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Mixed", "applicationDomains": ["General AI"], "area": "Safety & Trustworthiness", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/ZeroLoss-Lab/ELBench", "githubScope": "benchmark_repo", "githubStars": 3, "hfDailySubmittedAt": null, "hfDataset": "ZeroLoss-Lab/ELBench", "hfDatasetDownloads": 34, "hfDatasetLikes": 0, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2608.09548", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetLikes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfPaperUpvotes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "status": "fresh"}, "capabilities": [], "confidence": "High", "construction": "Aggregate Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "efb65a84f9e941745f3e6784878ce52e4a604593d16968449b1d92c1dde37136", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "ELBench is a benchmark for education-facing large language models, evaluating General Capability, Safety and Trustworthiness, Basic Education, and High-Level Cultivation under a common protocol with 2,939 items.", "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", "public artifact URL"], "snippet": "We introduce ELBench, the first benchmark to evaluate all four requirements (General Capability, Safety and Trustworthiness, Basic Education, and High-Level Cultivation) on the same models under a common protocol, combining curated public sources with newly synthesized safety and cultivation data."}, "familyId": "bmf_3e9cf94fe4c5", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 1, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "linked-from-data", "linkedUrl": "https://github.com/ZeroLoss-Lab/ELBench", "url": "https://huggingface.co/datasets/ZeroLoss-Lab/ELBench"}], "scope": "benchmark_repo", "url": "https://github.com/ZeroLoss-Lab/ELBench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_elbench_6c33e0fa", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/ZeroLoss-Lab/ELBench", "data": "https://huggingface.co/datasets/ZeroLoss-Lab/ELBench", "hfPaper": "https://huggingface.co/papers/2608.09548", "paper": "https://arxiv.org/abs/2608.09548", "pdf": "https://arxiv.org/pdf/2608.09548", "project": null, "report": "https://arxiv.org/abs/2608.09548"}, "metrics": [], "motivation": "Large language models are increasingly deployed in education as tutors, teaching assistants, and content generators.", "name": "ELBench", "oneLine": "ELBench is a benchmark for education-facing large language models, evaluating General Capability, Safety and Trustworthiness, Basic Education, and High-Level Cultivation under a common protocol with 2,939 items.", "paperTitle": "ELBench: A Multi-Dimensional Benchmark for Education-Facing Large Language Models", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.09548", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "ZeroLoss-Lab", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://huggingface.co/datasets/ZeroLoss-Lab/ELBench"}], "ranking": {"90d": {"confidence": "High", "coverage": 1.0, "datasetDownloadRank": 83, "datasetRankPopulation": 85, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.18504537701418716, "value": 3}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": 0.36612946919602324, "value": 34}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.0, "value": 0}}, "confidence": "High", "coverage": 1.0, "rank": 548, "score": 21}, "method": "attention-ranking-v13", "rank": 548, "score": 21}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-10", "source": {"authors": ["Yilin Jiang", "Xiaorong Zhu", "Fei Tan", "Zicheng Zhang", "Kaiyi Huang", "Yang Yu", "Zexuan Fei", "Yiming Luo", "Keqian Li", "Hao Hao", "Guangtao Zhai", "Aimin Zhou"], "categories": ["cs.CL", "cs.AI", "cs.CY"], "id": "2608.09548", "title": "ELBench: A Multi-Dimensional Benchmark for Education-Facing Large Language Models", "type": "arxiv", "url": "https://arxiv.org/abs/2608.09548"}, "sourceUpdatedAt": "2026-08-11T06:58:23Z", "topics": ["Safety"], "venueAttempts": [], "whyItMatters": "It fills the gap of integrated evaluation for education-facing models, which require accuracy, safety, instructional usefulness, and pedagogical alignment simultaneously."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": [{"key": "opencompass:2571", "name": "ELBench", "relation": "equivalent", "slug": "opencompass-2571-elbench", "source": "opencompass_hub"}]}
