{"record": {"aliases": ["ScienceArena: Benchmarking LLMs on Latest Scientific Olympiad Competitions"], "artifacts": [{"id": "arxiv:2608.30517", "kind": "paper", "url": "https://arxiv.org/abs/2608.30517"}, {"kind": "website", "url": "https://science-arena.onrender.com/"}], "authors": ["Guangxiang Zhao", "Qilong Shi", "Xusen Xiao", "Wenpu Liu", "Yaoming Li", "Linfeng Hao", "Shuyang Hou", "Zijian Guo", "Xinrui Zhang", "Yuntian Zhao", "Zhengyang Wang", "Wenrui Liu", "Yuhan Wu", "Tong Yang", "Lin Sun", "Xiangzheng Zhang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.30517", "source_url": "https://arxiv.org/abs/2608.30517"}, "categories": ["Language & Knowledge", "Materials & Chemistry", "Mathematics & Formal Science", "cs.AI"], "description": {"en": "Olympiad-style benchmark with open-ended physics, chemistry, and biology problems scored via rubrics and LLM judges."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.30517", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.30517", "title": "ScienceArena"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.30517", "modality": null, "name": "ScienceArena", "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": "true", "origin_record_id": "bm_sciencearena-benchmarking-llms-on-latest-s_c97e7adb", "origin_source": "arxiv", "recognition_confidence": "0.55", "record_sha256": "0d00ec6bf868e51730cadce9d6738728f6552871c73f4d497a5906328c5061e6", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-02T05:23:11.715633Z", "source_url": "https://arxiv.org/abs/2608.30517"}, "publisher": null, "released": "2026-08-31", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.30517", "source_url": "https://arxiv.org/abs/2608.30517"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-30517", "source": "claire_radar", "source_benchmark_id": "2608.30517", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["ScienceArena: Benchmarking LLMs on Latest Scientific Olympiad Competitions"], "annotation": "Unknown", "applicationDomains": ["Mathematics & Formal Science", "Materials & Chemistry"], "area": "Language & Knowledge", "attention": {"asOf": "2026-09-02", "attemptedAt": "2026-09-02T05:12:51.621571Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.30517", "observedAt": "2026-08-31T04:56:28.279469Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-09-02T05:12:51.621571Z", "state": "unavailable"}}, "status": "unavailable"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "Frontier LLM evaluation and bias towards fresh olympiad problems are likely to draw strong interest from the research community.", "score": 58}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-02T05:23:11.715633Z", "inputHash": "fa996308b70fc6a7abeddba16fe5f7510ca9f0786432831e9b3983893f07ef5d", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "We introduce \\textsc{ScienceArena}, an olympiad-style benchmark from thirteen public science competitions", "canonicalNameSource": "abstract", "decisionReason": "The paper describes an expert-audited pipeline, public competitions, and an interactive demo link, indicating an ongoing benchmark.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-02T05:23:11.715633Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Olympiad-style benchmark with open-ended physics, chemistry, and biology problems scored via rubrics and LLM judges.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["benchmark term in abstract", "benchmark release stated in one sentence", "public artifact URL"], "snippet": "We introduce \\textsc{ScienceArena}, an olympiad-style benchmark from thirteen public science competitions in physics, chemistry, and biology, including IPhO and IChO 2025--2026, IBO 2023, USAPhO 2026, and USNCO 2025."}, "familyId": "bmf_3297f50ef871", "firstSeenAt": "2026-09-01", "heat": null, "id": "bm_sciencearena-benchmarking-llms-on-latest-s_c97e7adb", "indexedAt": "2026-09-01T06:28:29.895112Z", "industrySectors": ["Materials & Chemicals"], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2608.30517", "pdf": "https://arxiv.org/pdf/2608.30517", "project": "https://science-arena.onrender.com/", "report": "https://arxiv.org/abs/2608.30517"}, "metrics": [], "motivation": "Benchmark saturation and data contamination increasingly obscure genuine scientific reasoning in frontier LLMs.", "name": "ScienceArena", "oneLine": "Olympiad-style benchmark with open-ended physics, chemistry, and biology problems scored via rubrics and LLM judges.", "paperTitle": "ScienceArena: Benchmarking LLMs on Latest Scientific Olympiad Competitions", "primaryDomain": "Mathematics & Formal Science", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.30517", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-01T06:28:29.895112Z"}, "publications": [], "publishers": [{"name": "ScienceArena Team", "organizationType": "benchmark-organization", "role": "benchmark-publisher", "sourceUrl": "https://science-arena.onrender.com/"}], "ranking": {"30d": {"confidence": "Low", "coverage": 0.0, "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": 30}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}, "90d": {"confidence": "Low", "coverage": 0.0, "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": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 0.55, "relation": "introduces", "releasedAt": "2026-08-31", "source": {"authors": ["Guangxiang Zhao", "Qilong Shi", "Xusen Xiao", "Wenpu Liu", "Yaoming Li", "Linfeng Hao", "Shuyang Hou", "Zijian Guo", "Xinrui Zhang", "Yuntian Zhao", "Zhengyang Wang", "Wenrui Liu", "Yuhan Wu", "Tong Yang", "Lin Sun", "Xiangzheng Zhang"], "categories": ["cs.AI", "cs.CL"], "id": "2608.30517", "title": "ScienceArena: Benchmarking LLMs on Latest Scientific Olympiad Competitions", "type": "arxiv", "url": "https://arxiv.org/abs/2608.30517"}, "sourceUpdatedAt": "2026-08-31T09:52:29Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Uses latest competition problems to reduce saturation and tests frontier LLMs' scientific reasoning."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
