CMATH: Can Your Language Model Pass Chinese Elementary School Math Test?
This study provides a benchmark for assessing LLMs' math abilities, exposing limitations in arithmetic and reasoning for model developers, though it is incremental as it applies existing methods to new data.
The authors tackled the problem of evaluating large language models' mathematical reasoning by creating the CMATH dataset of 1.7k Chinese elementary school math problems and found that only GPT-4 achieved at least 60% accuracy across all six grades, while other models struggled at various levels.
We present the Chinese Elementary School Math Word Problems (CMATH) dataset, comprising 1.7k elementary school-level math word problems with detailed annotations, source from actual Chinese workbooks and exams. This dataset aims to provide a benchmark tool for assessing the following question: to what grade level of elementary school math do the abilities of popular large language models (LLMs) correspond? We evaluate a variety of popular LLMs, including both commercial and open-source options, and discover that only GPT-4 achieves success (accuracy $\geq$ 60\%) across all six elementary school grades, while other models falter at different grade levels. Furthermore, we assess the robustness of several top-performing LLMs by augmenting the original problems in the CMATH dataset with distracting information. Our findings reveal that GPT-4 is able to maintains robustness, while other model fail. We anticipate that our study will expose limitations in LLMs' arithmetic and reasoning capabilities, and promote their ongoing development and advancement.