{"list":"other","total":64,"rows":[{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"2307.13854","title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","created":"2023-07-25","cited_by_count":2006},{"id":"2310.02255","title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","created":"2023-10-03","cited_by_count":1614},{"id":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413},{"id":"2404.07972","title":"OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments","created":"2024-04-11","cited_by_count":1195},{"id":"2311.12983","title":"GAIA: a benchmark for General AI Assistants","created":"2023-11-21","cited_by_count":1128},{"id":"2404.13076","title":"LLM Evaluators Recognize and Favor Their Own Generations","created":"2024-04-15","cited_by_count":686},{"id":"2504.12516","title":"BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents","created":"2025-04-16","cited_by_count":647},{"id":"2506.07982","title":"$\\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment","created":"2025-06-09","cited_by_count":627},{"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":"2407.18901","title":"AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents","created":"2024-07-26","cited_by_count":401},{"id":"2504.01848","title":"PaperBench: Evaluating AI's Ability to Replicate AI Research","created":"2025-04-02","cited_by_count":321},{"id":"2602.12670","title":"SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks","created":"2026-02-13","cited_by_count":315},{"id":"2411.04872","title":"FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI","created":"2024-11-07","cited_by_count":243},{"id":"2502.10517","title":"KernelBench: Can LLMs Write Efficient GPU Kernels?","created":"2025-02-14","cited_by_count":225},{"id":"2410.03859","title":"SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?","created":"2024-10-04","cited_by_count":203},{"id":"2505.11831","title":"ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems","created":"2025-05-17","cited_by_count":190},{"id":"2504.02605","title":"Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving","created":"2025-04-03","cited_by_count":171},{"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":"2409.07703","title":"DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?","created":"2024-09-12","cited_by_count":125},{"id":"2409.11363","title":"CORE-Bench: Fostering the Credibility of Published Research Through a Computational Reproducibility Agent Benchmark","created":"2024-09-17","cited_by_count":123},{"id":"2506.13651","title":"xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluations","created":"2025-06-16","cited_by_count":120},{"id":"2501.01257","title":"CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings","created":"2025-01-02","cited_by_count":115},{"id":"2502.12115","title":"SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?","created":"2025-02-17","cited_by_count":105},{"id":"2508.14704","title":"MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers","created":"2025-08-20","cited_by_count":96},{"id":"2602.16313","title":"MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks","created":"2026-02-18","cited_by_count":84},{"id":"2503.21934","title":"Proof or Bluff? Evaluating LLMs on 2025 USA Math Olympiad","created":"2025-03-27","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":"2510.21652","title":"AstaBench: Rigorous Benchmarking of AI Agents with a Scientific Research Suite","created":"2025-10-24","cited_by_count":53},{"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":"2505.24785","title":"EXP-Bench: Can AI Conduct AI Research Experiments?","created":"2025-05-30","cited_by_count":37},{"id":"2506.02314","title":"ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code","created":"2025-06-02","cited_by_count":36},{"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":"2602.13379","title":"Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents","created":"2026-02-13","cited_by_count":30},{"id":"2507.23486","title":"A Novel Evaluation Benchmark for Medical LLMs: Illuminating Safety and Effectiveness in Clinical Domains","created":"2025-07-31","cited_by_count":28},{"id":"2602.14721","title":"WebWorld: A Large-Scale World Model for Web Agent Training","created":"2026-02-16","cited_by_count":26},{"id":"2512.04324","title":"DAComp: Benchmarking Data Agents across the Full Data Intelligence Lifecycle","created":"2025-12-03","cited_by_count":23},{"id":"2602.15112","title":"ResearchGym: Evaluating Language Model Agents on Real-World AI Research","created":"2026-02-16","cited_by_count":22},{"id":"2602.11988","title":"Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents?","created":"2026-02-12","cited_by_count":20},{"id":"2602.14093","title":"GUI-GENESIS: Automated Synthesis of Efficient Environments with Verifiable Rewards for GUI Agent Post-Training","created":"2026-02-15","cited_by_count":18},{"id":"2602.16173","title":"Learning Personalized Agents from Human Feedback","created":"2026-02-18","cited_by_count":18},{"id":"2406.01623","title":"WebSuite: Systematically Evaluating Why Web Agents Fail","created":"2024-06-01","cited_by_count":16},{"id":"2502.15224","title":"Auto-Discovery-Bench: Diagnosing Structured State Tracking in Oracle-Guided Discovery","created":"2025-02-21","cited_by_count":16},{"id":"2602.12984","title":"SciAgentGym: Benchmarking Multi-Step Scientific Tool-use in LLM Agents","created":"2026-02-13","cited_by_count":15},{"id":"2602.17003","title":"Persona2Web: Benchmarking Personalized Web Agents for Contextual Reasoning with User History","created":"2026-02-19","cited_by_count":14},{"id":"2602.01655","title":"ProjDevBench: Benchmarking AI Coding Agents on End-to-End Project Development","created":"2026-02-02","cited_by_count":12},{"id":"2501.10711","title":"Code Benchmarks Should Prioritize Rigor, Reliability, and Reproducibility","created":"2025-01-18","cited_by_count":10},{"id":"2505.03570","title":"OSUniverse: Benchmark for Multimodal GUI-navigation AI Agents","created":"2025-05-06","cited_by_count":10},{"id":"2603.01203","title":"How Well Does Agent Development Reflect Real-World Work?","created":"2026-03-01","cited_by_count":10},{"id":"2512.08868","title":"EcomBench: Towards Holistic Evaluation of Foundation Agents in E-commerce","created":"2025-12-09","cited_by_count":8},{"id":"2602.12876","title":"BrowseComp-$V^3$: A Visual, Vertical, and Verifiable Benchmark for Multimodal Browsing Agents","created":"2026-02-13","cited_by_count":8},{"id":"2602.16662","title":"Evaluating Collective Behaviour of Hundreds of LLM Agents","created":"2026-02-18","cited_by_count":8},{"id":"2602.11750","title":"AmbiBench: Benchmarking Mobile GUI Agents Beyond One-Shot Instructions in the Wild","created":"2026-02-12","cited_by_count":7},{"id":"2602.12315","title":"AgenticShop: Benchmarking Agentic Product Curation for Personalized Web Shopping","created":"2026-02-12","cited_by_count":7},{"id":"2509.22237","title":"FeatBench: Towards More Realistic Evaluation of Feature-level Code Generation","created":"2025-09-26","cited_by_count":6},{"id":"2512.21373","title":"AInsteinBench: Benchmarking Coding Agents on Scientific Repositories","created":"2025-12-24","cited_by_count":6},{"id":"2602.12544","title":"Scaling Web Agent Training through Automatic Data Generation and Fine-grained Evaluation","created":"2026-02-13","cited_by_count":6},{"id":"2602.14135","title":"ForesightSafety Bench: A Frontier Risk Evaluation and Governance Framework towards Safe AI","created":"2026-02-15","cited_by_count":3},{"id":"2602.11786","title":"Evaluating LLM Safety Under Repeated Inference via Accelerated Prompt Stress Testing","created":"2026-02-12","cited_by_count":1},{"id":"2602.15019","title":"Hunt Globally: Wide Search AI Agents for Drug Asset Scouting in Investing, Business Development, and Competitive Intelligence","created":"2026-02-16","cited_by_count":1}],"next_cursor":null}