{"list":"other","total":92,"rows":[{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2307.13854","title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","created":"2023-07-25","cited_by_count":2006},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"2305.15334","title":"Gorilla: Large Language Model Connected with Massive APIs","created":"2023-05-24","cited_by_count":1332},{"id":"2311.12983","title":"GAIA: a benchmark for General AI Assistants","created":"2023-11-21","cited_by_count":1128},{"id":"2407.16741","title":"OpenHands: An Open Platform for AI Software Developers as Generalist Agents","created":"2024-07-23","cited_by_count":1002},{"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":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"2304.08244","title":"API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs","created":"2023-04-14","cited_by_count":591},{"id":"2601.11868","title":"Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces","created":"2026-01-17","cited_by_count":585},{"id":"2405.14573","title":"AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents","created":"2024-05-23","cited_by_count":468},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459},{"id":"2211.11501","title":"DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation","created":"2022-11-18","cited_by_count":452},{"id":"2401.13919","title":"WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models","created":"2024-01-25","cited_by_count":438},{"id":"1910.04867","title":"A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark","created":"2019-10-01","cited_by_count":425},{"id":"2407.01489","title":"Agentless: Demystifying LLM-based Software Engineering Agents","created":"2024-07-01","cited_by_count":421},{"id":"2103.14749","title":"Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks","created":"2021-03-26","cited_by_count":395},{"id":"2411.04368","title":"Measuring short-form factuality in large language models","created":"2024-11-07","cited_by_count":373},{"id":"2403.07718","title":"WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?","created":"2024-03-12","cited_by_count":363},{"id":"2111.15366","title":"AI and the Everything in the Whole Wide World Benchmark","created":"2021-11-26","cited_by_count":349},{"id":"2310.18018","title":"NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark","created":"2023-10-27","cited_by_count":348},{"id":"2203.07540","title":"ScienceWorld: Is your Agent Smarter than a 5th Grader?","created":"2022-03-14","cited_by_count":327},{"id":"2602.12670","title":"SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks","created":"2026-02-13","cited_by_count":315},{"id":"1806.11532","title":"TextWorld: A Learning Environment for Text-based Games","created":"2018-06-29","cited_by_count":310},{"id":"2402.14992","title":"tinyBenchmarks: evaluating LLMs with fewer examples","created":"2024-02-22","cited_by_count":310},{"id":"2506.11763","title":"DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents","created":"2025-06-13","cited_by_count":248},{"id":"2407.01502","title":"AI Agents That Matter","created":"2024-07-01","cited_by_count":219},{"id":"2406.04127","title":"Are We Done with MMLU?","created":"2024-06-06","cited_by_count":194},{"id":"2505.11831","title":"ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems","created":"2025-05-17","cited_by_count":190},{"id":"2402.05930","title":"WebLINX: Real-World Website Navigation with Multi-Turn Dialogue","created":"2024-02-08","cited_by_count":180},{"id":"2405.14782","title":"Lessons from the Trenches on Reproducible Evaluation of Language Models","created":"2024-05-23","cited_by_count":179},{"id":"2407.10362","title":"LAB-Bench: Measuring Capabilities of Language Models for Biology Research","created":"2024-07-14","cited_by_count":156},{"id":"2503.14499","title":"Measuring AI Ability to Complete Long Software Tasks","created":"2025-03-18","cited_by_count":156},{"id":"2411.00640","title":"Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluations","created":"2024-11-01","cited_by_count":148},{"id":"2406.12952","title":"SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents","created":"2024-06-18","cited_by_count":133},{"id":"2403.07714","title":"StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models","created":"2024-03-12","cited_by_count":132},{"id":"2405.10938","title":"Observational Scaling Laws and the Predictability of Language Model Performance","created":"2024-05-17","cited_by_count":130},{"id":"2511.04703","title":"Measuring what Matters: Construct Validity in Large Language Model Benchmarks","created":"2025-11-03","cited_by_count":119},{"id":"2309.16289","title":"LawBench: Benchmarking Legal Knowledge of Large Language Models","created":"2023-09-28","cited_by_count":117},{"id":"2411.12990","title":"BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices","created":"2024-11-20","cited_by_count":114},{"id":"2406.14991","title":"SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation","created":"2024-06-21","cited_by_count":111},{"id":"2506.14866","title":"OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents","created":"2025-06-17","cited_by_count":111},{"id":"2410.06992","title":"SWE-Bench+: Enhanced Coding Benchmark for LLMs","created":"2024-10-09","cited_by_count":99},{"id":"2503.00096","title":"BixBench: a Comprehensive Benchmark for LLM-based Agents in Computational Biology","created":"2025-02-28","cited_by_count":89},{"id":"2309.08638","title":"Anchor Points: Benchmarking Models with Much Fewer Examples","created":"2023-09-14","cited_by_count":86},{"id":"2501.10970","title":"The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs","created":"2025-01-19","cited_by_count":74},{"id":"2501.12851","title":"ACEBench: Who Wins the Match Point in Tool Usage?","created":"2025-01-22","cited_by_count":71},{"id":"2504.20879","title":"The Leaderboard Illusion","created":"2025-04-29","cited_by_count":66},{"id":"2501.14654","title":"MedAgentBench: A Realistic Virtual EHR Environment to Benchmark Medical LLM Agents","created":"2025-01-24","cited_by_count":62},{"id":"2605.03546","title":"ProgramBench: Can Language Models Rebuild Programs From Scratch?","created":"2026-05-05","cited_by_count":59},{"id":"2410.07331","title":"DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models","created":"2024-10-09","cited_by_count":58},{"id":"2411.17501","title":"The Limits of Inference Scaling Through Resampling","created":"2024-11-26","cited_by_count":53},{"id":"2505.19253","title":"DeepResearchGym: A Free, Transparent, and Reproducible Evaluation Sandbox for Deep Research","created":"2025-05-25","cited_by_count":53},{"id":"2503.15223","title":"Are \"Solved Issues\" in SWE-bench Really Solved Correctly? An Empirical Study","created":"2025-03-19","cited_by_count":49},{"id":"2506.12286","title":"The SWE-Bench Illusion: When State-of-the-Art LLMs Remember Instead of Reason","created":"2025-06-14","cited_by_count":49},{"id":"2602.03587","title":"CL-bench: A Benchmark for Context Learning","created":"2026-02-03","cited_by_count":47},{"id":"2505.15055","title":"Lost in Benchmarks? Rethinking Large Language Model Benchmarking with Item Response Theory","created":"2025-05-21","cited_by_count":45},{"id":"2506.09289","title":"UTBoost: Rigorous Evaluation of Coding Agents on SWE-Bench","created":"2025-06-10","cited_by_count":45},{"id":"2403.08604","title":"Prompting Large Language Models to Tackle the Full Software Development Lifecycle: A Case Study","created":"2024-03-13","cited_by_count":44},{"id":"2306.10062","title":"Revealing the structure of language model capabilities","created":"2023-06-14","cited_by_count":40},{"id":"2407.12844","title":"metabench -- A Sparse Benchmark of Reasoning and Knowledge in Large Language Models","created":"2024-07-04","cited_by_count":39},{"id":"2504.13359","title":"Cost-of-Pass: An Economic Framework for Evaluating Language Models","created":"2025-04-17","cited_by_count":35},{"id":"2508.04482","title":"OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use","created":"2025-08-06","cited_by_count":35},{"id":"2509.11106","title":"Fluid Language Model Benchmarking","created":"2025-09-14","cited_by_count":35},{"id":"2602.10975","title":"FeatureBench: Benchmarking Agentic Coding for Complex Feature Development","created":"2026-02-11","cited_by_count":34},{"id":"2602.14337","title":"LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces","created":"2026-02-15","cited_by_count":34},{"id":"2505.14615","title":"SATBench: Benchmarking LLMs' Logical Reasoning via Automated Puzzle Generation from SAT Formulas","created":"2025-05-20","cited_by_count":33},{"id":"2406.08723","title":"ECBD: Evidence-Centered Benchmark Design for NLP","created":"2024-06-13","cited_by_count":28},{"id":"2506.07673","title":"How Benchmark Prediction from Fewer Data Misses the Mark","created":"2025-06-09","cited_by_count":28},{"id":"2407.13696","title":"Do These LLM Benchmarks Agree? Fixing Benchmark Evaluation with BenchBench","created":"2024-07-18","cited_by_count":27},{"id":"2504.11442","title":"TextArena","created":"2025-04-15","cited_by_count":27},{"id":"2204.13653","title":"GRIT: General Robust Image Task Benchmark","created":"2022-04-28","cited_by_count":26},{"id":"2510.01051","title":"GEM: A Gym for Agentic LLMs","created":"2025-10-01","cited_by_count":23},{"id":"2512.15699","title":"FrontierCS: Evolving Challenges for Evolving Intelligence","created":"2025-12-17","cited_by_count":23},{"id":"2501.13953","title":"Redundancy Principles for MLLMs Benchmarks","created":"2025-01-20","cited_by_count":19},{"id":"2503.21557","title":"debug-gym: A Text-Based Environment for Interactive Debugging","created":"2025-03-27","cited_by_count":19},{"id":"2505.20981","title":"RefAV: Towards Planning-Centric Scenario Mining","created":"2025-05-27","cited_by_count":13},{"id":"2508.09093","title":"Scaling Up Active Testing to Large Language Models","created":"2025-08-12","cited_by_count":13},{"id":"2510.23191","title":"The Benchmarking Epistemology: Validity Theory for Evaluating Machine Learning Models","created":"2025-10-27","cited_by_count":13},{"id":"2504.15707","title":"RePOPE: Impact of Annotation Errors on the POPE Benchmark","created":"2025-04-22","cited_by_count":9},{"id":"2507.20208","title":"From Benchmarks to Skills: Low-Rank Factors for LLM Evaluation","created":"2025-07-27","cited_by_count":9},{"id":"2510.08730","title":"How Reliable is Language Model Micro-Benchmarking?","created":"2025-10-09","cited_by_count":9},{"id":"2604.04192","title":"Graphic-Design-Bench: A Comprehensive Benchmark for Evaluating AI on Graphic Design Tasks","created":"2026-04-05","cited_by_count":8},{"id":"2504.02810","title":"Generative Evaluation of Complex Reasoning in Large Language Models","created":"2025-04-03","cited_by_count":6},{"id":"2601.11077","title":"ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development","created":"2026-01-16","cited_by_count":6},{"id":"2606.24020","title":"You Don't Need to Run Every Eval","created":"2026-06-22","cited_by_count":3},{"id":"2506.09813","title":"Metritocracy: Representative Metrics for Lite Benchmarks","created":"2025-06-11","cited_by_count":2}],"next_cursor":null}