{"total":23,"rows":[{"id":"2505.15146","title":"lmgame-Bench: How Good are LLMs at Playing Games?","created":"2025-05-21","cited_by_count":55,"area":null},{"id":"2603.20633","title":"Seed1.8 Model Card: Towards Generalized Real-World Agency","created":"2026-03-21","cited_by_count":50,"area":null},{"id":"2505.17399","title":"FullFront: Benchmarking MLLMs Across the Full Front-End Engineering Workflow","created":"2025-05-23","cited_by_count":28,"area":null},{"id":"2505.12589","title":"SurveillanceVQA-589K: A Benchmark for Comprehensive Surveillance Video-Language Understanding with Large Models","created":"2025-05-19","cited_by_count":18,"area":null},{"id":"2505.24138","title":"AMSbench: A Comprehensive Benchmark for Evaluating MLLM Capabilities in AMS Circuits","created":"2025-05-30","cited_by_count":15,"area":null},{"id":"2503.14478","title":"Creation-MMBench: Assessing Context-Aware Creative Intelligence in MLLM","created":"2025-03-18","cited_by_count":14,"area":null},{"id":"2511.01163","title":"ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation","created":"2025-11-03","cited_by_count":13,"area":null},{"id":"2602.07096","title":"RealFin: How Well Do LLMs Reason About Finance When Users Leave Things Unsaid?","created":"2026-02-06","cited_by_count":9,"area":null},{"id":"2506.04585","title":"MuSciClaims: Multimodal Scientific Claim Verification","created":"2025-06-05","cited_by_count":8,"area":null},{"id":"2509.21079","title":"SoM-1K: A Thousand-Problem Benchmark Dataset for Strength of Materials","created":"2025-09-25","cited_by_count":8,"area":null},{"id":"2505.05026","title":"Do MLLMs Capture How Interfaces Guide User Behavior? A Benchmark for Multimodal UI/UX Design Understanding","created":"2025-05-08","cited_by_count":3,"area":null},{"id":"2602.09839","title":"ARK: A Dual-Axis Multimodal Retrieval Benchmark along Reasoning and Knowledge","created":"2026-02-10","cited_by_count":3,"area":null},{"id":"2603.13427","title":"MIBench: Evaluating LMMs on Multimodal Interaction","created":"2026-03-13","cited_by_count":2,"area":null},{"id":"2603.21573","title":"Rethinking Visual Privacy: A Compositional Privacy Risk Framework for Severity Assessment with VLMs","created":"2026-03-23","cited_by_count":2,"area":null},{"id":"2608.21504","title":"ChemDIRT: A Diversified Instruction, Representation, and Task Benchmark for Robust Chemistry-LLM Evaluation","created":"2026-08-21","cited_by_count":2,"area":null},{"id":"2511.15830","title":"Mini Amusement Parks (MAPs): A Testbed for Modelling Business Decisions","created":"2025-11-19","cited_by_count":1,"area":null},{"id":"2603.26839","title":"From Pixels to BFS: High Maze Accuracy Does Not Imply Visual Planning","created":"2026-03-27","cited_by_count":1,"area":null},{"id":"2609.02864","title":"Thinking in Pictures: A Systematic Benchmark for Reasoning-driven Image Generation","created":"2026-09-02","cited_by_count":1,"area":null},{"id":"2608.06361","title":"The Low Frequency Trap: Video Language Models Fail at Simple Event Bookkeeping","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.26495","title":"Video-FLAIR: Not Whether to Reason, But How","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.33399","title":"SciGen-Verifier: A Multimodal Reasoner for Explainable Verification in Scientific Image Generation","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.38851","title":"Where MLLMs Fail and Why: Causal Task Decomposition for Capability Failure Diagnosis","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.14542","title":"Are Multimodal Benchmarks Really Useful? Item-Level Multimodal Benchmark Diagnosis via Structure-Response Co-Calibration","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}