{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VIREIP6T7XXO4YFWZRZINEATNY","short_pith_number":"pith:VIREIP6T","schema_version":"1.0","canonical_sha256":"aa22443fd3fdeeee60b6cc728690136e09e19606f527406526bac0f9d782c47d","source":{"kind":"arxiv","id":"2406.16772","version":2},"attestation_state":"computed","paper":{"title":"OlympicArena Medal Ranks: Who Is the Most Intelligent AI So Far?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Pengfei Liu, Shijie Xia, Zengzhi Wang, Zhen Huang","submitted_at":"2024-06-24T16:31:12Z","abstract_excerpt":"In this report, we pose the following question: Who is the most intelligent AI model to date, as measured by the OlympicArena (an Olympic-level, multi-discipline, multi-modal benchmark for superintelligent AI)? We specifically focus on the most recently released models: Claude-3.5-Sonnet, Gemini-1.5-Pro, and GPT-4o. For the first time, we propose using an Olympic medal Table approach to rank AI models based on their comprehensive performance across various disciplines. Empirical results reveal: (1) Claude-3.5-Sonnet shows highly competitive overall performance over GPT-4o, even surpassing GPT-"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.16772","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T16:31:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c8287ed81853b2547afa627ff5e7ba31756ec0792170463339231821e8f31b41","abstract_canon_sha256":"adbd8269e8b321b53600e3231d3e39585ba66fd80654f30122c40138be24293b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:07.431356Z","signature_b64":"lSP8/NLldisyI95ZsBCtiyH358unHfbfuTG6lVFjZ32DdOAApWu3bODyRzDv5yGUh10gC3G4z+dZ4YCYXw5JBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa22443fd3fdeeee60b6cc728690136e09e19606f527406526bac0f9d782c47d","last_reissued_at":"2026-07-05T08:37:07.430892Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:07.430892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OlympicArena Medal Ranks: Who Is the Most Intelligent AI So Far?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Pengfei Liu, Shijie Xia, Zengzhi Wang, Zhen Huang","submitted_at":"2024-06-24T16:31:12Z","abstract_excerpt":"In this report, we pose the following question: Who is the most intelligent AI model to date, as measured by the OlympicArena (an Olympic-level, multi-discipline, multi-modal benchmark for superintelligent AI)? We specifically focus on the most recently released models: Claude-3.5-Sonnet, Gemini-1.5-Pro, and GPT-4o. For the first time, we propose using an Olympic medal Table approach to rank AI models based on their comprehensive performance across various disciplines. Empirical results reveal: (1) Claude-3.5-Sonnet shows highly competitive overall performance over GPT-4o, even surpassing GPT-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16772","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.16772/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.16772","created_at":"2026-07-05T08:37:07.430949+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.16772v2","created_at":"2026-07-05T08:37:07.430949+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16772","created_at":"2026-07-05T08:37:07.430949+00:00"},{"alias_kind":"pith_short_12","alias_value":"VIREIP6T7XXO","created_at":"2026-07-05T08:37:07.430949+00:00"},{"alias_kind":"pith_short_16","alias_value":"VIREIP6T7XXO4YFW","created_at":"2026-07-05T08:37:07.430949+00:00"},{"alias_kind":"pith_short_8","alias_value":"VIREIP6T","created_at":"2026-07-05T08:37:07.430949+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.02871","citing_title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2502.03387","citing_title":"LIMO: Less is More for Reasoning","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2602.21697","citing_title":"EditFlow: Benchmarking and Optimizing Code Edit Recommendation Systems via Reconstruction of Developer Flows","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VIREIP6T7XXO4YFWZRZINEATNY","json":"https://pith.science/pith/VIREIP6T7XXO4YFWZRZINEATNY.json","graph_json":"https://pith.science/api/pith-number/VIREIP6T7XXO4YFWZRZINEATNY/graph.json","events_json":"https://pith.science/api/pith-number/VIREIP6T7XXO4YFWZRZINEATNY/events.json","paper":"https://pith.science/paper/VIREIP6T"},"agent_actions":{"view_html":"https://pith.science/pith/VIREIP6T7XXO4YFWZRZINEATNY","download_json":"https://pith.science/pith/VIREIP6T7XXO4YFWZRZINEATNY.json","view_paper":"https://pith.science/paper/VIREIP6T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.16772&json=true","fetch_graph":"https://pith.science/api/pith-number/VIREIP6T7XXO4YFWZRZINEATNY/graph.json","fetch_events":"https://pith.science/api/pith-number/VIREIP6T7XXO4YFWZRZINEATNY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VIREIP6T7XXO4YFWZRZINEATNY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VIREIP6T7XXO4YFWZRZINEATNY/action/storage_attestation","attest_author":"https://pith.science/pith/VIREIP6T7XXO4YFWZRZINEATNY/action/author_attestation","sign_citation":"https://pith.science/pith/VIREIP6T7XXO4YFWZRZINEATNY/action/citation_signature","submit_replication":"https://pith.science/pith/VIREIP6T7XXO4YFWZRZINEATNY/action/replication_record"}},"created_at":"2026-07-05T08:37:07.430949+00:00","updated_at":"2026-07-05T08:37:07.430949+00:00"}