{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.11683", "kind": "paper", "url": "https://arxiv.org/abs/2608.11683"}], "authors": ["Yuhao Zhang", "O. Ozan Koyluoglu", "Thejas Venkatesh", "Richard Diehl Martinez", "Vishank Bhatia", "Arash Alidoust", "Ashwin Paranjape"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.11683", "source_url": "https://arxiv.org/abs/2608.11683"}, "categories": ["Finance", "Language & Knowledge", "cs.AI"], "description": {"en": "Comprises 220 expert-crafted queries with 11,543 source-attributed rubrics across six finance use cases, evaluating agents on open-ended analyst-style answers via rubric-based grading."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.11683", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.11683", "title": "FrontierFinance"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.11683", "modality": null, "name": "FrontierFinance", "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_frontierfinance_f2f44751", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "8416290140cb431a75f136f91f539c1105baf0e560480aa5afb8b454a3cb46ae", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.11683"}, "publisher": null, "released": "2026-08-12", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.11683", "source_url": "https://arxiv.org/abs/2608.11683"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-11683", "source": "claire_radar", "source_benchmark_id": "2608.11683", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Finance"], "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": 0, "hfPaperUrl": "https://huggingface.co/papers/2608.11683", "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", "lastSuccessfulDate": "2026-09-30", "state": "stale"}}, "status": "stale"}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-21T04:30:40.934319Z", "inputHash": "7fd3ddaacac95ccc812e5910cf0938dc4d139d8776cfa1f2e38ca412fda17376", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Comprises 220 expert-crafted queries with 11,543 source-attributed rubrics across six finance use cases, evaluating agents on open-ended analyst-style answers via rubric-based grading.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence"], "snippet": "We introduce FrontierFinance, a fully open benchmark of 220 expert-crafted queries and 11,543 source-attributed rubrics spanning six crucial use cases across the full investor workflow."}, "familyId": "bmf_d3024ba14951", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_frontierfinance_f2f44751", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Financial Services"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.11683", "paper": "https://arxiv.org/abs/2608.11683", "pdf": "https://arxiv.org/pdf/2608.11683", "project": null, "report": "https://arxiv.org/abs/2608.11683"}, "metrics": [], "motivation": "AI agents are increasingly deployed for professional investment research, yet no benchmark captures the complexity of the full investor workflow.", "name": "FrontierFinance", "oneLine": "Comprises 220 expert-crafted queries with 11,543 source-attributed rubrics across six finance use cases, evaluating agents on open-ended analyst-style answers via rubric-based grading.", "paperTitle": "FrontierFinance: A Challenging Benchmark for Measuring Frontier Intelligence of Finance Agents", "primaryDomain": "Finance", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.11683", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "Samaya AI", "organizationType": "company-research-lab", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2608.11683"}], "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": 0.0, "value": 0}}, "confidence": "Low", "coverage": 0.15, "rank": null, "score": 43}, "method": "attention-ranking-v13", "rank": null, "score": 43}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-12", "source": {"authors": ["Yuhao Zhang", "O. Ozan Koyluoglu", "Thejas Venkatesh", "Richard Diehl Martinez", "Vishank Bhatia", "Arash Alidoust", "Ashwin Paranjape"], "categories": ["cs.AI", "cs.CL"], "id": "2608.11683", "title": "FrontierFinance: A Challenging Benchmark for Measuring Frontier Intelligence of Finance Agents", "type": "arxiv", "url": "https://arxiv.org/abs/2608.11683"}, "sourceUpdatedAt": "2026-08-12T05:43:26Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Captures the full investor workflow beyond narrow data extraction, offering a harder and broader evaluation that assesses agent quality and efficiency in realistic finance research."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
