Chinese SimpleQA (C-SimpleQA) is a Chinese-language benchmark for evaluating the factuality of large language models on short question answering. It was designed to be diverse and high-quality: it covers six major topics with 99 diverse subtopics, uses static (time-stable) reference answers, and includes a thorough quality-control process to ensure reliable evaluation. The dataset is provided in JSON format and is intended for easy, reproducible evaluation of model factuality on short Chinese questions. License: CC BY-NC-SA 4.0.
No results indexed yet — be the first to submit a score.
Submit a checkpoint and a reproduction script. We will run it, publish the score, and — if it takes the top — annotate the step on the progress chart with your name.