{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FRJ3HHYIWDAMXDDWYCCHHFAO6Q","short_pith_number":"pith:FRJ3HHYI","schema_version":"1.0","canonical_sha256":"2c53b39f08b0c0cb8c76c08473940ef436e2b446e9800fbd3d8aa67c194021d3","source":{"kind":"arxiv","id":"2304.06364","version":2},"attestation_state":"computed","paper":{"title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"AGIEval benchmark shows GPT-4 surpassing average humans on SAT math at 95 percent and LSAT.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Amin Saied, Nan Duan, Ruixiang Cui, Shuai Lu, Wanjun Zhong, Weizhu Chen, Yanlin Wang, Yaobo Liang, Yiduo Guo","submitted_at":"2023-04-13T09:39:30Z","abstract_excerpt":"Evaluating the general abilities of foundation models to tackle human-level tasks is a vital aspect of their development and application in the pursuit of Artificial General Intelligence (AGI). Traditional benchmarks, which rely on artificial datasets, may not accurately represent human-level capabilities. In this paper, we introduce AGIEval, a novel benchmark specifically designed to assess foundation model in the context of human-centric standardized exams, such as college entrance exams, law school admission tests, math competitions, and lawyer qualification tests. We evaluate several state"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2304.06364","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-13T09:39:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7f2904bd4ffe5ce96b3b972e1fc8a8968dd88d028084d4c7c8955b278e7f449e","abstract_canon_sha256":"ec90ca1ff59448b9db5895e41cc3b23fbad0354bb6abf73b36ab1cb6cf7a9874"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:48.257154Z","signature_b64":"ejqvxDIZ11uGstVmswye68n/vSAVK5FJw1mGZSL6R10JoMuS7cEHpSo/KPfzxDY9qbxQX2udZkcBectxc3OFAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c53b39f08b0c0cb8c76c08473940ef436e2b446e9800fbd3d8aa67c194021d3","last_reissued_at":"2026-05-17T23:38:48.256487Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:48.256487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"AGIEval benchmark shows GPT-4 surpassing average humans on SAT math at 95 percent and LSAT.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Amin Saied, Nan Duan, Ruixiang Cui, Shuai Lu, Wanjun Zhong, Weizhu Chen, Yanlin Wang, Yaobo Liang, Yiduo Guo","submitted_at":"2023-04-13T09:39:30Z","abstract_excerpt":"Evaluating the general abilities of foundation models to tackle human-level tasks is a vital aspect of their development and application in the pursuit of Artificial General Intelligence (AGI). Traditional benchmarks, which rely on artificial datasets, may not accurately represent human-level capabilities. In this paper, we introduce AGIEval, a novel benchmark specifically designed to assess foundation model in the context of human-centric standardized exams, such as college entrance exams, law school admission tests, math competitions, and lawyer qualification tests. We evaluate several state"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"GPT-4 surpasses average human performance on SAT, LSAT, and math competitions, attaining a 95% accuracy rate on the SAT Math test and a 92.5% accuracy on the English test of the Chinese national college entrance exam.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That standardized human exams are valid and representative proxies for general human-level cognitive capabilities without significant selection bias or format advantages for current model architectures.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"AGIEval shows GPT-4 exceeding average human scores on SAT Math at 95% and Chinese college entrance English at 92.5%, while revealing weaker results on complex reasoning tasks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"AGIEval benchmark shows GPT-4 surpassing average humans on SAT math at 95 percent and LSAT.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d7b2d23d251b913928ce3f45aa96b82d7a80957aa443931c8947354c3da3b233"},"source":{"id":"2304.06364","kind":"arxiv","version":2},"verdict":{"id":"35bdc164-9f80-46b8-8082-15b60c51cf65","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T09:59:54.385025Z","strongest_claim":"GPT-4 surpasses average human performance on SAT, LSAT, and math competitions, attaining a 95% accuracy rate on the SAT Math test and a 92.5% accuracy on the English test of the Chinese national college entrance exam.","one_line_summary":"AGIEval shows GPT-4 exceeding average human scores on SAT Math at 95% and Chinese college entrance English at 92.5%, while revealing weaker results on complex reasoning tasks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That standardized human exams are valid and representative proxies for general human-level cognitive capabilities without significant selection bias or format advantages for current model architectures.","pith_extraction_headline":"AGIEval benchmark shows GPT-4 surpassing average humans on SAT math at 95 percent and LSAT."},"references":{"count":287,"sample":[{"doi":"10.24963/ijcai.2022/629","year":2022,"title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence,","work_id":"c4f3637d-3692-46a9-bfea-c7bd6b57ae7f","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics , pages=","work_id":"c6b78093-c72e-47cb-afc3-1e6df42e13ca","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"2023 , publisher =","work_id":"ec5f4dd4-c17c-4ada-92fd-e4e521e15710","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Communications of the ACM , volume=","work_id":"d5c1eec5-fe7c-47e3-b110-9b2ca7817689","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=","work_id":"83cfc672-4920-4faa-8e23-5c30b4777e6f","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":287,"snapshot_sha256":"82933c7ffcb95de91c268d61a400ba36d7f656730ad69d223ad26b41a33716bc","internal_anchors":12},"formal_canon":{"evidence_count":2,"snapshot_sha256":"0957bd48e13f7caae39084c23b61c2e1a362a81a1c84c48e796139f1b6f376fa"},"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":"2304.06364","created_at":"2026-05-17T23:38:48.256606+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.06364v2","created_at":"2026-05-17T23:38:48.256606+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.06364","created_at":"2026-05-17T23:38:48.256606+00:00"},{"alias_kind":"pith_short_12","alias_value":"FRJ3HHYIWDAM","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"FRJ3HHYIWDAMXDDW","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"FRJ3HHYI","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":41,"internal_anchor_count":41,"sample":[{"citing_arxiv_id":"2309.10305","citing_title":"Baichuan 2: Open Large-scale Language Models","ref_index":82,"is_internal_anchor":true},{"citing_arxiv_id":"2310.06825","citing_title":"Mistral 7B","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2401.04088","citing_title":"Mixtral of Experts","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2402.03300","citing_title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","ref_index":61,"is_internal_anchor":true},{"citing_arxiv_id":"2409.06624","citing_title":"A Practice of Post-Training on Llama-3 70B with Optimal Selection of Additional Language Mixture Ratio","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2501.05465","citing_title":"Small Language Models (SLMs) Can Still Pack a Punch: A survey (updated 2026)","ref_index":156,"is_internal_anchor":true},{"citing_arxiv_id":"2504.16155","citing_title":"PRIMETIME : Limits of LLMs in Temporal Primitives","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2506.12119","citing_title":"Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2509.19590","citing_title":"Position: AI Evaluations Should be Grounded on a Theory of Capability","ref_index":56,"is_internal_anchor":true},{"citing_arxiv_id":"2509.22739","citing_title":"Painless Activation Steering: An Automated, Lightweight Approach for Post-Training Large Language Models","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2510.12773","citing_title":"Dr.LLM: Dynamic Layer Routing in LLMs","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2408.04840","citing_title":"mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models","ref_index":78,"is_internal_anchor":true},{"citing_arxiv_id":"2502.10248","citing_title":"Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model","ref_index":135,"is_internal_anchor":true},{"citing_arxiv_id":"2507.22359","citing_title":"League of LLMs: A Benchmark-Free Paradigm for Mutual Evaluation of Large Language Models","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2507.00432","citing_title":"Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning","ref_index":200,"is_internal_anchor":true},{"citing_arxiv_id":"2511.05501","citing_title":"Towards Real-World Validity in Generative AI Benchmarks: Understanding and Designing Domain-Centered Evaluations for Journalism Practitioners","ref_index":71,"is_internal_anchor":true},{"citing_arxiv_id":"2311.04257","citing_title":"mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration","ref_index":76,"is_internal_anchor":true},{"citing_arxiv_id":"2503.04697","citing_title":"L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2309.05653","citing_title":"MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning","ref_index":72,"is_internal_anchor":true},{"citing_arxiv_id":"2406.11794","citing_title":"DataComp-LM: In search of the next generation of training sets for language models","ref_index":220,"is_internal_anchor":true},{"citing_arxiv_id":"2512.14554","citing_title":"VLegal-Bench: Cognitively Grounded Benchmark for Vietnamese Legal Reasoning of Large Language Models","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2311.16867","citing_title":"The Falcon Series of Open Language Models","ref_index":226,"is_internal_anchor":true},{"citing_arxiv_id":"2406.11931","citing_title":"DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2406.11931","citing_title":"DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2401.01614","citing_title":"GPT-4V(ision) is a Generalist Web Agent, if Grounded","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FRJ3HHYIWDAMXDDWYCCHHFAO6Q","json":"https://pith.science/pith/FRJ3HHYIWDAMXDDWYCCHHFAO6Q.json","graph_json":"https://pith.science/api/pith-number/FRJ3HHYIWDAMXDDWYCCHHFAO6Q/graph.json","events_json":"https://pith.science/api/pith-number/FRJ3HHYIWDAMXDDWYCCHHFAO6Q/events.json","paper":"https://pith.science/paper/FRJ3HHYI"},"agent_actions":{"view_html":"https://pith.science/pith/FRJ3HHYIWDAMXDDWYCCHHFAO6Q","download_json":"https://pith.science/pith/FRJ3HHYIWDAMXDDWYCCHHFAO6Q.json","view_paper":"https://pith.science/paper/FRJ3HHYI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.06364&json=true","fetch_graph":"https://pith.science/api/pith-number/FRJ3HHYIWDAMXDDWYCCHHFAO6Q/graph.json","fetch_events":"https://pith.science/api/pith-number/FRJ3HHYIWDAMXDDWYCCHHFAO6Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FRJ3HHYIWDAMXDDWYCCHHFAO6Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FRJ3HHYIWDAMXDDWYCCHHFAO6Q/action/storage_attestation","attest_author":"https://pith.science/pith/FRJ3HHYIWDAMXDDWYCCHHFAO6Q/action/author_attestation","sign_citation":"https://pith.science/pith/FRJ3HHYIWDAMXDDWYCCHHFAO6Q/action/citation_signature","submit_replication":"https://pith.science/pith/FRJ3HHYIWDAMXDDWYCCHHFAO6Q/action/replication_record"}},"created_at":"2026-05-17T23:38:48.256606+00:00","updated_at":"2026-05-17T23:38:48.256606+00:00"}