{"record": {"aliases": ["LLM-SoccerArena: Benchmarking LLMs on Real-World Predictions in Sports"], "artifacts": [{"id": "arxiv:2607.24573", "kind": "paper", "url": "https://arxiv.org/abs/2607.24573"}, {"kind": "website", "url": "https://llm-soccerarena.com"}], "authors": ["Jonas Schröder", "Jonas Schweisthal", "Oliver Müller", "Markus Weinmann", "Stefan Feuerriegel"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.24573", "source_url": "https://arxiv.org/abs/2607.24573"}, "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "A prospective live benchmark in which LLMs forecast unresolved sports events. Forecasts are timestamped and schema-validated, then scored against the real outcomes."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.24573", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.24573", "title": "LLM-SoccerArena"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["LMU Klinikum", "Ludwig-Maximilians-Universität München", "Paderborn University", "University of Cologne"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.24573", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.24573", "source_url": "https://openalex.org/W7171556166"}, "key": "claire-radar:2607.24573", "modality": null, "name": "LLM-SoccerArena", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"admission_policy_version": "2026-09-09.1", "confidence": "Medium", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-09-25T04:40:22Z", "data_status": "primary-source-indexed", "display_eligible": "true", "origin_record_id": "bm_llm-soccerarena-benchmarking-llms-on-real-_ca86e931", "origin_source": "arxiv", "recognition_confidence": "0.55", "record_sha256": "393dcbff445824b6198cf44bcdaa05eb07a0bb85407d8b92425d29691ca09168", "relation": "introduces", "review_model": "claude-code-default", "review_state": "ai-reviewed", "reviewed_at": "2026-09-24T20:47:08.095326Z", "source_url": "https://arxiv.org/abs/2607.24573"}, "publisher": null, "released": "2026-07-27", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.24573", "source_url": "https://arxiv.org/abs/2607.24573"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-24573", "source": "claire_radar", "source_benchmark_id": "2607.24573", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["LLM-SoccerArena: Benchmarking LLMs on Real-World Predictions in Sports"], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "The recent World Cup evaluation and the live, continuously updated platform may draw attention.", "score": 45}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-24T20:47:08.095326Z", "inputHash": "ea453171973adf451ffba309c15695bd548739738b6403f93085be7af8199d2c", "model": "claude-code-default"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "LLM-SoccerArena: Benchmarking LLMs on Real-World Predictions in Sports", "canonicalNameSource": "paper_title", "decisionReason": "The benchmark is named, forecasts are scored with the Brier score against real outcomes, and the source describes a public open-source platform with a project link.", "evaluationEvidence": {"reuse": "a public open-source platform", "scoring": "a 0.023 improvement in Brier score", "task": "a prospective live benchmark that evaluates how well LLMs forecast real-world sports events before the outcomes are known"}, "model": "claude-code-default", "reviewedAt": "2026-09-24T20:47:08.095326Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "A prospective live benchmark in which LLMs forecast unresolved sports events. Forecasts are timestamped and schema-validated, then scored against the real outcomes.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["benchmark term in abstract", "benchmark release stated in one sentence", "public artifact URL"], "snippet": "We introduce LLM-SoccerArena (https://llm-soccerarena.com), a prospective live benchmark that evaluates how well LLMs forecast real-world sports events before the outcomes are known."}, "familyId": "bmf_640a904f2635", "firstSeenAt": "2026-08-19", "heat": null, "id": "bm_llm-soccerarena-benchmarking-llms-on-real-_ca86e931", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2607.24573", "pdf": "https://arxiv.org/pdf/2607.24573", "project": "https://llm-soccerarena.com", "report": "https://arxiv.org/abs/2607.24573"}, "metrics": [], "motivation": "Large language models (LLMs) increasingly support decisions about uncertain future events, yet evaluating their ability to forecast real-world outcomes remains difficult.", "name": "LLM-SoccerArena", "oneLine": "A prospective live benchmark in which LLMs forecast unresolved sports events. Forecasts are timestamped and schema-validated, then scored against the real outcomes.", "paperTitle": "LLM-SoccerArena: Benchmarking LLMs on Real-World Predictions in Sports", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.24573", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-19T11:05:13.395391Z"}, "publications": [], "readiness": "Paper only", "recognitionConfidence": 0.55, "relation": "introduces", "releasedAt": "2026-07-27", "reviewLifecycle": {"state": "pending"}, "source": {"authors": ["Jonas Schr\\\"oder", "Jonas Schweisthal", "Oliver M\\\"uller", "Markus Weinmann", "Stefan Feuerriegel"], "categories": ["cs.AI"], "id": "2607.24573", "title": "LLM-SoccerArena: Benchmarking LLMs on Real-World Predictions in Sports", "type": "arxiv", "url": "https://arxiv.org/abs/2607.24573"}, "sourceUpdatedAt": "2026-07-27T15:38:29Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Because it scores forecasts made before outcomes are known, the benchmark avoids retrospective data leakage and can be rerun for future tournaments and leagues."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
