{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.14989", "kind": "paper", "url": "https://arxiv.org/abs/2607.14989"}], "authors": ["Chengyu Shen", "Yujie Fu", "Gangtao Xin", "Yanheng Hou", "Wenlong Fei", "Guojie Zhu", "Jiawei Li", "Hongcheng Gao", "Runming He", "Zhen Hao Wong", "Meiyi Qiang", "Hao Liang", "Zhao Cao", "Hao Jiang", "Chong Chen", "Wentao Zhang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.14989", "source_url": "https://arxiv.org/abs/2607.14989"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "The evaluation object is unclear from the provided information."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.14989", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.14989", "title": "OmniaBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2607.14989", "modality": null, "name": "OmniaBench", "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_omniabench_e9e6c4ef", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "81d4a1d732a8b5280fddcb09a6ae7eda6cb5d34fa8faff51beab2183e866ad16", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.14989"}, "publisher": null, "released": "2026-07-16", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.14989", "source_url": "https://arxiv.org/abs/2607.14989"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-14989", "source": "claire_radar", "source_benchmark_id": "2607.14989", "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": 1, "hfPaperUrl": "https://huggingface.co/papers/2607.14989", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "status": "fresh"}, "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": "7321f5df32355b8eef13cea8752328e05bfff2efcd49f269f6958cbab05ea239", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "The evaluation object is unclear from the provided information.", "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 introduce OmniaBench, a benchmark for evaluating general agents across diverse scenarios with explicit state spaces."}, "familyId": "bmf_6ab9ee1bd426", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_omniabench_e9e6c4ef", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.14989", "paper": "https://arxiv.org/abs/2607.14989", "pdf": "https://arxiv.org/pdf/2607.14989", "project": null, "report": "https://arxiv.org/abs/2607.14989"}, "metrics": [], "motivation": "Large language models are increasingly evolving from text generators into general agents capable of understanding user requests, invoking external tools, and completing complex tasks through interaction.", "name": "OmniaBench", "oneLine": "The evaluation object is unclear from the provided information.", "paperTitle": "OmniaBench: Benchmarking General AI Agents Across Diverse Scenarios", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.14989", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.15, "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": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.12247537038455211, "value": 1}}, "confidence": "Low", "coverage": 0.15, "rank": null, "score": 44}, "method": "attention-ranking-v13", "rank": null, "score": 44}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-16", "source": {"authors": ["Chengyu Shen", "Yujie Fu", "Gangtao Xin", "Yanheng Hou", "Wenlong Fei", "Guojie Zhu", "Jiawei Li", "Hongcheng Gao", "Runming He", "Zhen Hao Wong", "Meiyi Qiang", "Hao Liang", "Zhao Cao", "Hao Jiang", "Chong Chen", "Wentao Zhang"], "categories": ["cs.CL", "cs.AI"], "id": "2607.14989", "title": "OmniaBench: Benchmarking General AI Agents Across Diverse Scenarios", "type": "arxiv", "url": "https://arxiv.org/abs/2607.14989"}, "sourceUpdatedAt": "2026-07-16T13:38:07Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "The evaluation gap and practical decision value are unclear."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
