{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.04549", "kind": "paper", "url": "https://arxiv.org/abs/2608.04549"}], "authors": ["Pau Arnal", "Khaled Denfir", "Danylo Smahliuk", "Amrut Avhad", "Marcus A. Castro"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.04549", "source_url": "https://arxiv.org/abs/2608.04549"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "EuroExec is an expert-authored benchmark of 413 open-ended European executive tasks evaluated by human experts. It uses a multi-attribute rubric and preference ranking to compute a Solve Rate."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.04549", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.04549", "title": "EuroExec"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.04549", "modality": null, "name": "EuroExec", "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_euroexec_53125f62", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "1273456233a67c960a2de8c50362ef0b273d8016b978878a23e397852601fc62", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.04549"}, "publisher": null, "released": "2026-08-05", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.04549", "source_url": "https://arxiv.org/abs/2608.04549"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-04549", "source": "claire_radar", "source_benchmark_id": "2608.04549", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Mixed", "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": 0, "hfPaperUrl": "https://huggingface.co/papers/2608.04549", "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": "Medium", "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": "b52fc3bf1603b151ec3e788412ca59c9da373be792b76784774be06a631a88a9", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "EuroExec is an expert-authored benchmark of 413 open-ended European executive tasks evaluated by human experts. It uses a multi-attribute rubric and preference ranking to compute a Solve Rate.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "evaluation protocol evidence"], "snippet": "We dedicate more than 4,000 human expert hours to evaluate a selection of six frontier LLMs on a member of this class of problems: EuroExec, our introduced human expert-based benchmark composed of 413 open-ended long-form European executive tasks authored by 47 vetted domain experts, each question drawn from experience in a real case."}, "familyId": "bmf_2d0194cba00a", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_euroexec_53125f62", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.04549", "paper": "https://arxiv.org/abs/2608.04549", "pdf": "https://arxiv.org/pdf/2608.04549", "project": null, "report": "https://arxiv.org/abs/2608.04549"}, "metrics": [], "motivation": "Frontier LLMs are increasingly put to use on open-ended complex questions, different in nature from the ones they are typically evaluated on.", "name": "EuroExec", "oneLine": "EuroExec is an expert-authored benchmark of 413 open-ended European executive tasks evaluated by human experts. It uses a multi-attribute rubric and preference ranking to compute a Solve Rate.", "paperTitle": "EuroExec: Frontier Language Models Fall Short of Expert Judgment on European Executive Decision Tasks", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.04549", "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": 0.0, "value": 0}}, "confidence": "Low", "coverage": 0.15, "rank": null, "score": 43}, "method": "attention-ranking-v13", "rank": null, "score": 43}}, "readiness": "Paper only", "recognitionConfidence": 0.85, "relation": "introduces", "releasedAt": "2026-08-05", "source": {"authors": ["Pau Arnal", "Khaled Denfir", "Danylo Smahliuk", "Amrut Avhad", "Marcus A. Castro"], "categories": ["cs.CL", "cs.AI", "cs.LG"], "id": "2608.04549", "title": "EuroExec: Frontier Language Models Fall Short of Expert Judgment on European Executive Decision Tasks", "type": "arxiv", "url": "https://arxiv.org/abs/2608.04549"}, "sourceUpdatedAt": "2026-08-06T11:12:23Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "It addresses evaluation of open-ended, complex tasks where subjective judgment is key, but the lack of public artifacts makes its reuse uncertain."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
