{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.24155", "kind": "paper", "url": "https://arxiv.org/abs/2606.24155"}], "authors": ["Jinru Ding", "Chuchu Jiang", "Lu Lu", "Wenrao Pang", "Mouxiao Bian", "Zhuangzhi Gao", "Jiangyuan Chen", "Xinwei Peng", "Ruiyao Chen", "Sijie Ren", "Renjie Lu", "Yun Zhong", "Bin Han", "Meiling Liu", "Jie Xu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.24155", "source_url": "https://arxiv.org/abs/2606.24155"}, "categories": ["Agents", "Biology & Drug Discovery", "Multimodal"], "description": {"en": "MedBench v5 evaluates clinical multimodal models across 63 tasks with process-oriented metrics including stressors and hallucination tracking."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.24155", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.24155", "title": "MedBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Shanghai Artificial Intelligence Laboratory"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.24155", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.24155", "source_url": "https://openalex.org/W7165768301"}, "key": "claire-radar:2606.24155", "modality": null, "name": "MedBench", "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_medbench_c5b43204", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "9072973abcee8e821dce413bf8e85d96b8ea7f0e915ec62795e94e6a1dd230df", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.24155"}, "publisher": null, "released": "2026-06-23", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.24155", "source_url": "https://arxiv.org/abs/2606.24155"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-24155", "source": "claire_radar", "source_benchmark_id": "2606.24155", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Biology & Drug Discovery"], "area": "Multimodal", "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/2606.24155", "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": "3f5ec9ae3c543561fed00836ed0e0126898a6bbee8aa121270d4d71de598a871", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "MedBench v5 evaluates clinical multimodal models across 63 tasks with process-oriented metrics including stressors and hallucination tracking.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce MedBench v5, a redesigned benchmark for clinical multimodal models (language, vision-language, and agent systems) that moves from static QA to dynamic, process-oriented evaluation."}, "familyId": "bmf_9629d422c4d1", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_medbench_c5b43204", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.24155", "paper": "https://arxiv.org/abs/2606.24155", "pdf": "https://arxiv.org/pdf/2606.24155", "project": null, "report": "https://arxiv.org/abs/2606.24155"}, "metrics": [], "motivation": "Existing medical AI benchmarks lack process visibility, atomic skill evaluation, and integrated hallucination detection.", "name": "MedBench", "oneLine": "MedBench v5 evaluates clinical multimodal models across 63 tasks with process-oriented metrics including stressors and hallucination tracking.", "paperTitle": "MedBench v5: A Dynamic, Process-Oriented, and Hallucination-Aware Benchmark for Clinical Multimodal Models", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.24155", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-23", "source": {"authors": ["Jinru Ding", "Chuchu Jiang", "Lu Lu", "Wenrao Pang", "Mouxiao Bian", "Zhuangzhi Gao", "Jiangyuan Chen", "Xinwei Peng", "Ruiyao Chen", "Sijie Ren", "Renjie Lu", "Yun Zhong", "Bin Han", "Meiling Liu", "and Jie Xu"], "categories": ["cs.CL"], "id": "2606.24155", "title": "MedBench v5: A Dynamic, Process-Oriented, and Hallucination-Aware Benchmark for Clinical Multimodal Models", "type": "arxiv", "url": "https://arxiv.org/abs/2606.24155"}, "sourceUpdatedAt": "2026-07-06T09:18:28Z", "topics": ["Agents", "Multimodal"], "venueAttempts": [], "whyItMatters": "Addresses gaps in process visibility and hallucination detection in medical AI evaluation, offering a unified framework for capability profiling and stress testing."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
