Large language models (LLMs) have shown strong performance on medical question answering benchmarks, yet existing evaluations remain limited in assessing longitudinal clinical reasoning across multiple hospital admissions. We introduce ChronoClinQA, a large-scale benchmark for longitudinal clinical reasoning grounded in multi-admission electronic health records. Built from longitudinal discharge summaries in MIMIC-IV-Note, ChronoClinQA contains 15,067 QA pairs spanning six clinically grounded reasoning dimensions and three complementary question formats: open-ended, adversarial, and unanswerable multiple-choice questions. Each instance requires reasoning over temporally accumulated patient trajectories, with contexts averaging over 16K tokens across up to eight hospital admissions. Experiments on both general-purpose and medical LLMs reveal substantial performance degradation in longitudinal and adversarial settings, highlighting persistent challenges in integrating cross-admission evidence and in temporal clinical reasoning. Our findings position ChronoClinQA as a challenging benchmark for advancing clinically grounded long-context reasoning in medical LLMs.

Recent advancements in 2D multimodal large language models (MLLMs) have significantly improved performance in vision-language tasks. However, extending these capabilities to 3D environments remains a distinct challenge due to the complexity of spatial reasoning. Nevertheless, existing 3D benchmarks often lack fine-grained numerical reasoning task annotations, limiting MLLMs’ ability to perform precise spatial measurements and complex numerical reasoning. To address this gap, we introduce NUMINA, the first Natural Understanding benchmark for Multi-dimensional Intelligence and Numerical reasoning Abilities to enhance multimodal indoor perceptual understanding. NUMINA features multi-scale annotations and various question-answer pairs, generated using NUMINA-Flow, an automated annotation pipeline that integrates LLM rewriting and rule-based self-verification. We evaluate the performance of various state-of-the-art LLMs on NUMINA following the Chat-Scene framework, demonstrating that current LLMs struggle with multimodal numerical reasoning, particularly in performing precise computations such as distance and volume estimation, highlighting the need for further advancements in 3D models. The dataset and source codes can be obtained from https://github.com/fengshun124/NUMINA.