{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2605.29833", "kind": "paper", "url": "https://arxiv.org/abs/2605.29833"}], "authors": ["Wanhao Liu", "Jiaqing Xie", "Qian Tan", "Weida Wang", "Jue Wang", "Ran Sun", "Zhuo Yang", "Wanli Ouyang", "Lei Bai", "Tianfan Fu", "Lu Chen", "Xin Chen", "Yuqiang Li"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2605.29833", "source_url": "https://arxiv.org/abs/2605.29833"}, "categories": ["Materials & Chemistry", "Multimodal", "Reasoning"], "description": {"en": "OmniMatBench assesses multimodal reasoning in materials science across 19 subfields with 3,171 expert-curated QA and calculation problems, spanning four domains from fundamental knowledge to applied materials."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2605.29833", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2605.29833", "title": "OmniMatBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of Science and Technology of China", "Shanghai Artificial Intelligence Laboratory", "Fudan University", "Southeast University", "Nanjing University", "Shanghai Jiao Tong University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2605.29833", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2605.29833", "source_url": "https://openalex.org/W7162767581"}, "key": "claire-radar:2605.29833", "modality": null, "name": "OmniMatBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "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_omnimatbench_4692794c", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "b078351adef7acc6abb9265df3e7683d5d2f68226cad98ce3ee93fc69156db33", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2605.29833"}, "publisher": null, "released": "2026-05-28", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2605.29833", "source_url": "https://arxiv.org/abs/2605.29833"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2605-29833", "source": "claire_radar", "source_benchmark_id": "2605.29833", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Materials & Chemistry"], "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/2605.29833", "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": ["Reasoning"], "confidence": "Medium", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "9a8d275f49a4b7bd2cb17b9132e25608cb7d483caf39f5e464bff3ba54d93e26", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "OmniMatBench assesses multimodal reasoning in materials science across 19 subfields with 3,171 expert-curated QA and calculation problems, spanning four domains from fundamental knowledge to applied materials.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence"], "snippet": "To fill this gap, we present OmniMatBench, a human-calibrated multimodal reasoning benchmark for materials science."}, "familyId": "bmf_e2542c6f5f83", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_omnimatbench_4692794c", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Materials & Chemicals"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2605.29833", "paper": "https://arxiv.org/abs/2605.29833", "pdf": "https://arxiv.org/pdf/2605.29833", "project": null, "report": "https://arxiv.org/abs/2605.29833"}, "metrics": [], "motivation": "As multimodal language models play an increasingly important role in scientific research, materials science offers a critical testbed due to its interdisciplinary, multimodal, and application-driven nature.", "name": "OmniMatBench", "oneLine": "OmniMatBench assesses multimodal reasoning in materials science across 19 subfields with 3,171 expert-curated QA and calculation problems, spanning four domains from fundamental knowledge to applied materials.", "paperTitle": "OmniMatBench: A Human-Calibrated Multimodal Reasoning Benchmark Across 19 Materials Science Subfields", "primaryDomain": "Materials & Chemistry", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2605.29833", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 0.85, "relation": "introduces", "releasedAt": "2026-05-28", "source": {"authors": ["Wanhao Liu", "Jiaqing Xie", "Qian Tan", "Weida Wang", "Jue Wang", "Ran Sun", "Zhuo Yang", "Wanli Ouyang", "Lei Bai", "Tianfan Fu", "Lu Chen", "Xin Chen", "Yuqiang Li"], "categories": ["cs.AI"], "id": "2605.29833", "title": "OmniMatBench: A Human-Calibrated Multimodal Reasoning Benchmark Across 19 Materials Science Subfields", "type": "arxiv", "url": "https://arxiv.org/abs/2605.29833"}, "sourceUpdatedAt": "2026-05-29T03:29:38Z", "topics": ["Multimodal", "Reasoning"], "venueAttempts": [], "whyItMatters": "Existing materials benchmarks focus on narrow tasks; OmniMatBench provides a broad reasoning benchmark revealing a substantial gap in current MLLMs, guiding AI assistant development in materials research."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
