{"list":"other","total":78,"rows":[{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004},{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"2206.14858","title":"Solving Quantitative Reasoning Problems with Language Models","created":"2022-06-29","cited_by_count":1392},{"id":"2009.13081","title":"What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams","created":"2020-09-28","cited_by_count":1356},{"id":"2311.07911","title":"Instruction-Following Evaluation for Large Language Models","created":"2023-11-14","cited_by_count":1228},{"id":"1606.06031","title":"The LAMBADA dataset: Word prediction requiring a broad discourse context","created":"2016-06-20","cited_by_count":992},{"id":"1903.00161","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","created":"2019-03-01","cited_by_count":903},{"id":"1902.01007","title":"Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference","created":"2019-02-04","cited_by_count":876},{"id":"1704.04683","title":"RACE: Large-scale ReAding Comprehension Dataset From Examinations","created":"2017-04-15","cited_by_count":861},{"id":"1910.14599","title":"Adversarial NLI: A New Benchmark for Natural Language Understanding","created":"2019-10-31","cited_by_count":807},{"id":"2003.11080","title":"XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization","created":"2020-03-24","cited_by_count":742},{"id":"2304.06364","title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","created":"2023-04-13","cited_by_count":716},{"id":"2305.08322","title":"C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models","created":"2023-05-15","cited_by_count":708},{"id":"2506.07982","title":"$\\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment","created":"2025-06-09","cited_by_count":627},{"id":"2106.03193","title":"The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation","created":"2021-06-06","cited_by_count":560},{"id":"2210.03057","title":"Language Models are Multilingual Chain-of-Thought Reasoners","created":"2022-10-06","cited_by_count":530},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459},{"id":"1808.07036","title":"QuAC : Question Answering in Context","created":"2018-08-21","cited_by_count":381},{"id":"2411.04368","title":"Measuring short-form factuality in large language models","created":"2024-11-07","cited_by_count":373},{"id":"2111.15366","title":"AI and the Everything in the Whole Wide World Benchmark","created":"2021-11-26","cited_by_count":349},{"id":"2308.11462","title":"LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models","created":"2023-08-20","cited_by_count":336},{"id":"2308.16884","title":"The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants","created":"2023-08-31","cited_by_count":311},{"id":"2406.19314","title":"LiveBench: A Challenging, Contamination-Limited LLM Benchmark","created":"2024-06-27","cited_by_count":262},{"id":"2411.04872","title":"FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI","created":"2024-11-07","cited_by_count":243},{"id":"2402.03927","title":"Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs","created":"2024-02-06","cited_by_count":229},{"id":"2112.08608","title":"QuALITY: Question Answering with Long Input Texts, Yes!","created":"2021-12-16","cited_by_count":208},{"id":"2406.04127","title":"Are We Done with MMLU?","created":"2024-06-06","cited_by_count":194},{"id":"2412.03304","title":"Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation","created":"2024-12-04","cited_by_count":191},{"id":"2505.11831","title":"ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems","created":"2025-05-17","cited_by_count":190},{"id":"2309.07445","title":"SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects","created":"2023-09-14","cited_by_count":152},{"id":"2311.09783","title":"Investigating Data Contamination in Modern Benchmarks for Large Language Models","created":"2023-11-16","cited_by_count":138},{"id":"2402.01781","title":"When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards","created":"2024-02-01","cited_by_count":137},{"id":"2208.08227","title":"MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generation","created":"2022-08-17","cited_by_count":136},{"id":"2411.12990","title":"BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices","created":"2024-11-20","cited_by_count":114},{"id":"1906.04701","title":"HEAD-QA: A Healthcare Dataset for Complex Reasoning","created":"2019-06-11","cited_by_count":101},{"id":"2407.17436","title":"AIR-Bench 2024: A Safety Benchmark Based on Risk Categories from Regulations and Policies","created":"2024-07-11","cited_by_count":74},{"id":"2203.04592","title":"Mapping global dynamics of benchmark creation and saturation in artificial intelligence","created":"2022-03-09","cited_by_count":71},{"id":"2505.10573","title":"Measurement to Meaning: A Validity-Centered Framework for AI Evaluation","created":"2025-05-13","cited_by_count":57},{"id":"2506.11928","title":"LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming?","created":"2025-06-13","cited_by_count":55},{"id":"2509.07968","title":"SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge","created":"2025-09-09","cited_by_count":54},{"id":"2501.03200","title":"The FACTS Grounding Leaderboard: Benchmarking LLMs' Ability to Ground Responses to Long-Form Input","created":"2025-01-06","cited_by_count":52},{"id":"2507.02856","title":"Answer Matching Outperforms Multiple Choice for Language Model Evaluation","created":"2025-07-03","cited_by_count":41},{"id":"2502.17407","title":"Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoning","created":"2025-02-24","cited_by_count":37},{"id":"2407.16711","title":"Benchmarks as Microscopes: A Call for Model Metrology","created":"2024-07-22","cited_by_count":35},{"id":"2309.08632","title":"Pretraining on the Test Set Is All You Need","created":"2023-09-13","cited_by_count":33},{"id":"2406.08723","title":"ECBD: Evidence-Centered Benchmark Design for NLP","created":"2024-06-13","cited_by_count":28},{"id":"2305.09022","title":"It Takes Two to Tango: Navigating Conceptualizations of NLP Tasks and Measurements of Performance","created":"2023-05-15","cited_by_count":26},{"id":"2401.14698","title":"Under the Surface: Tracking the Artifactuality of LLM-Generated Data","created":"2024-01-26","cited_by_count":24},{"id":"2405.19522","title":"Artificial Intelligence Index Report 2024","created":"2024-05-29","cited_by_count":24},{"id":"2410.20245","title":"Improving Model Evaluation using SMART Filtering of Benchmark Datasets","created":"2024-10-26","cited_by_count":21},{"id":"2503.01622","title":"DOVE: A Large-Scale Multi-Dimensional Predictions Dataset Towards Meaningful LLM Evaluation","created":"2025-03-03","cited_by_count":21},{"id":"2407.21530","title":"Data Contamination Report from the 2024 CONDA Shared Task","created":"2024-07-31","cited_by_count":20},{"id":"2412.05520","title":"More than Marketing? On the Information Value of AI Benchmarks for Practitioners","created":"2024-12-07","cited_by_count":17},{"id":"2311.02807","title":"QualEval: Qualitative Evaluation for Model Improvement","created":"2023-11-06","cited_by_count":11},{"id":"2502.19412","title":"The Mighty ToRR: A Benchmark for Table Reasoning and Robustness","created":"2025-02-26","cited_by_count":10},{"id":"2410.11672","title":"Leaving the barn door open for Clever Hans: Simple features predict LLM benchmark answers","created":"2024-10-15","cited_by_count":9},{"id":"2505.06108","title":"LLMs Outperform Experts on Challenging Biology Benchmarks","created":"2025-05-09","cited_by_count":9},{"id":"2505.22830","title":"What Has Been Lost with Synthetic Evaluation?","created":"2025-05-28","cited_by_count":9},{"id":"2602.03344","title":"Robustness as an Emergent Property of Task Performance","created":"2026-02-03","cited_by_count":2}],"next_cursor":null}