{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RLI6ARNPX5PWAUF7QWZAPSSCXW","short_pith_number":"pith:RLI6ARNP","schema_version":"1.0","canonical_sha256":"8ad1e045afbf5f6050bf85b207ca42bda5f27be94e10621488196130a1286ac1","source":{"kind":"arxiv","id":"2305.12474","version":3},"attestation_state":"computed","paper":{"title":"Evaluating the Performance of Large Language Models on GAOKAO Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Large language models achieve competitive scores on the Chinese GAOKAO exam but vary widely by subject.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chunyang Li, Liang He, Xiaotian Zhang, Xipeng Qiu, Yi Zong, Zhengyu Ying","submitted_at":"2023-05-21T14:39:28Z","abstract_excerpt":"Large Language Models(LLMs) have demonstrated remarkable performance across various natural language processing tasks; however, how to comprehensively and accurately assess their performance becomes an urgent issue to be addressed. This paper introduces GAOKAO-Bench, an intuitive benchmark that employs questions from the Chinese GAOKAO examination as test samples, including both subjective and objective questions. To align with human examination methods, we design a method based on zero-shot settings to evaluate the performance of LLMs. With human evaluation, we obtain the converted total scor"},"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":"2305.12474","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-21T14:39:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e837fe6ef607afdc534a14dee6ec69abb75d423d278e34ba67aff1c544e6c953","abstract_canon_sha256":"074e0a9cd4babe7f97f7ce2bdaf6a075a0d6b98e6d8b35c99eb9422629c11d85"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:14.111105Z","signature_b64":"+QwMVdk3UE509wPAmlMSjLJvfiE98qslb6aGOy8UDiEN80St9dEdZfMSsoQez/O0KLl9xn/ZfH8f4IKzUry8Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ad1e045afbf5f6050bf85b207ca42bda5f27be94e10621488196130a1286ac1","last_reissued_at":"2026-05-17T23:38:14.110393Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:14.110393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating the Performance of Large Language Models on GAOKAO Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Large language models achieve competitive scores on the Chinese GAOKAO exam but vary widely by subject.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chunyang Li, Liang He, Xiaotian Zhang, Xipeng Qiu, Yi Zong, Zhengyu Ying","submitted_at":"2023-05-21T14:39:28Z","abstract_excerpt":"Large Language Models(LLMs) have demonstrated remarkable performance across various natural language processing tasks; however, how to comprehensively and accurately assess their performance becomes an urgent issue to be addressed. This paper introduces GAOKAO-Bench, an intuitive benchmark that employs questions from the Chinese GAOKAO examination as test samples, including both subjective and objective questions. To align with human examination methods, we design a method based on zero-shot settings to evaluate the performance of LLMs. With human evaluation, we obtain the converted total scor"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our findings reveal that LLMs have achieved competitive scores in Chinese GAOKAO examination, while they exhibit significant performance disparities across various subjects.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That zero-shot prompting on GAOKAO questions produces answers whose quality can be fairly compared to human exam performance via human grading.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LLMs achieve competitive scores on GAOKAO exam questions but display large performance gaps across subjects.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Large language models achieve competitive scores on the Chinese GAOKAO exam but vary widely by subject.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"df4ba602b5a9d223f86614794c90e9047c55cef1fe19b4099ce0dae61944b78d"},"source":{"id":"2305.12474","kind":"arxiv","version":3},"verdict":{"id":"91ab21aa-fd8c-4cc4-9200-d8fac4b26310","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T12:23:54.910620Z","strongest_claim":"Our findings reveal that LLMs have achieved competitive scores in Chinese GAOKAO examination, while they exhibit significant performance disparities across various subjects.","one_line_summary":"LLMs achieve competitive scores on GAOKAO exam questions but display large performance gaps across subjects.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That zero-shot prompting on GAOKAO questions produces answers whose quality can be fairly compared to human exam performance via human grading.","pith_extraction_headline":"Large language models achieve competitive scores on the Chinese GAOKAO exam but vary widely by subject."},"references":{"count":19,"sample":[{"doi":"","year":null,"title":"Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt","work_id":"7165db1f-9442-4e9a-8a0d-43246db1d50f","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","ref_index":2,"cited_arxiv_id":"2303.08774","is_internal_anchor":true},{"doi":"","year":2016,"title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","ref_index":3,"cited_arxiv_id":"2206.04615","is_internal_anchor":true},{"doi":"","year":null,"title":"加强管理：对凤堰古梯田保护区内的 游客进行管理，设置必要的警示标志， 禁止破坏梯田、采摘植物等行为。同 时，加强对古建筑民居群落、古寨堡、 古庙宇、古堰渠、古塘坝等文物遗存的 保护，防止游客在参观过程中对这些文 物遗存造成损害。","work_id":"d2bc52d5-0e2a-4d73-969b-b1c554bb984b","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"推广科普：在凤堰古梯田保护区内设 置科普展板，向游客介绍梯田的历史、 文化和生态环境，提高游客的文化素养 和环保意识，减少游客对梯田的破坏。","work_id":"9092f07e-a3ec-40f2-992c-08aa61280c2b","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":19,"snapshot_sha256":"b4dbbfe8698ddc22faeb70b9c09b1445219cfc9f134f6d507ff9023e4f4dc5e8","internal_anchors":2},"formal_canon":{"evidence_count":2,"snapshot_sha256":"eaf4a1530db43077596a47ebb42222e7b5856c83cba5f6c88f5b8ab7ea7e71ff"},"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":"2305.12474","created_at":"2026-05-17T23:38:14.110489+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.12474v3","created_at":"2026-05-17T23:38:14.110489+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12474","created_at":"2026-05-17T23:38:14.110489+00:00"},{"alias_kind":"pith_short_12","alias_value":"RLI6ARNPX5PW","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"RLI6ARNPX5PWAUF7","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"RLI6ARNP","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":18,"sample":[{"citing_arxiv_id":"2507.00432","citing_title":"Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning","ref_index":207,"is_internal_anchor":true},{"citing_arxiv_id":"2411.10442","citing_title":"Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization","ref_index":116,"is_internal_anchor":true},{"citing_arxiv_id":"2603.18472","citing_title":"Cognitive Mismatch in Multimodal Large Language Models for Discrete Symbol Understanding","ref_index":121,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16392","citing_title":"RoMathExam: A Longitudinal Dataset of Romanian Math Exams (1895-2025) with a Seven-Decade Core (1957-2025)","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2512.15745","citing_title":"LLaDA2.0: Scaling Up Diffusion Language Models to 100B","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2403.04652","citing_title":"Yi: Open Foundation Models by 01.AI","ref_index":92,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26644","citing_title":"When to Vote, When to Rewrite: Disagreement-Guided Strategy Routing for Test-Time Scaling","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09635","citing_title":"K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08904","citing_title":"OPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search Spaces","ref_index":63,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04078","citing_title":"Validity-Calibrated Reasoning Distillation","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04078","citing_title":"Validity-Calibrated Reasoning Distillation","ref_index":56,"is_internal_anchor":true},{"citing_arxiv_id":"2401.02954","citing_title":"DeepSeek LLM: Scaling Open-Source Language Models with Longtermism","ref_index":129,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08948","citing_title":"TaxPraBen: A Scalable Benchmark for Structured Evaluation of LLMs in Chinese Real-World Tax Practice","ref_index":61,"is_internal_anchor":true},{"citing_arxiv_id":"2405.04434","citing_title":"DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model","ref_index":121,"is_internal_anchor":true},{"citing_arxiv_id":"2504.10479","citing_title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","ref_index":150,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13515","citing_title":"SFT-GRPO Data Overlap as a Post-Training Hyperparameter for Autoformalization","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2508.18265","citing_title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","ref_index":178,"is_internal_anchor":true},{"citing_arxiv_id":"2604.20140","citing_title":"HiPO: Hierarchical Preference Optimization for Adaptive Reasoning in LLMs","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RLI6ARNPX5PWAUF7QWZAPSSCXW","json":"https://pith.science/pith/RLI6ARNPX5PWAUF7QWZAPSSCXW.json","graph_json":"https://pith.science/api/pith-number/RLI6ARNPX5PWAUF7QWZAPSSCXW/graph.json","events_json":"https://pith.science/api/pith-number/RLI6ARNPX5PWAUF7QWZAPSSCXW/events.json","paper":"https://pith.science/paper/RLI6ARNP"},"agent_actions":{"view_html":"https://pith.science/pith/RLI6ARNPX5PWAUF7QWZAPSSCXW","download_json":"https://pith.science/pith/RLI6ARNPX5PWAUF7QWZAPSSCXW.json","view_paper":"https://pith.science/paper/RLI6ARNP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.12474&json=true","fetch_graph":"https://pith.science/api/pith-number/RLI6ARNPX5PWAUF7QWZAPSSCXW/graph.json","fetch_events":"https://pith.science/api/pith-number/RLI6ARNPX5PWAUF7QWZAPSSCXW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RLI6ARNPX5PWAUF7QWZAPSSCXW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RLI6ARNPX5PWAUF7QWZAPSSCXW/action/storage_attestation","attest_author":"https://pith.science/pith/RLI6ARNPX5PWAUF7QWZAPSSCXW/action/author_attestation","sign_citation":"https://pith.science/pith/RLI6ARNPX5PWAUF7QWZAPSSCXW/action/citation_signature","submit_replication":"https://pith.science/pith/RLI6ARNPX5PWAUF7QWZAPSSCXW/action/replication_record"}},"created_at":"2026-05-17T23:38:14.110489+00:00","updated_at":"2026-05-17T23:38:14.110489+00:00"}