Saved in:
Bibliographic Details
Main Authors: Wang, Ruonan, Wang, Runxi, Shen, Yunwen, Wu, Chengfeng, Zhou, Qinglin, Chandra, Rohitash
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.00309
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915363497705472
author Wang, Ruonan
Wang, Runxi
Shen, Yunwen
Wu, Chengfeng
Zhou, Qinglin
Chandra, Rohitash
author_facet Wang, Ruonan
Wang, Runxi
Shen, Yunwen
Wu, Chengfeng
Zhou, Qinglin
Chandra, Rohitash
contents Large Language Models (LLMs) have shown impressive performance on a range of educational tasks, but are still understudied for their potential to solve mathematical problems. In this study, we compare three prominent LLMs, including GPT-4o, DeepSeek-V3, and Gemini-2.0, on three mathematics datasets of varying complexities (GSM8K, MATH500, and MIT Open Courseware datasets). We take a five-dimensional approach based on the Structured Chain-of-Thought (SCoT) framework to assess final answer correctness, step completeness, step validity, intermediate calculation accuracy, and problem comprehension. The results show that GPT-4o is the most stable and consistent in performance across all the datasets, but particularly it performs outstandingly in high-level questions of the MIT Open Courseware dataset. DeepSeek-V3 is competitively strong in well-structured domains such as optimisation, but suffers from fluctuations in accuracy in statistical inference tasks. Gemini-2.0 shows strong linguistic understanding and clarity in well-structured problems but performs poorly in multi-step reasoning and symbolic logic. Our error analysis reveals particular deficits in each model: GPT-4o is at times lacking in sufficient explanation or precision; DeepSeek-V3 leaves out intermediate steps; and Gemini-2.0 is less flexible in mathematical reasoning in higher dimensions.
format Preprint
id arxiv_https___arxiv_org_abs_2506_00309
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Evaluation of LLMs for mathematical problem solving
Wang, Ruonan
Wang, Runxi
Shen, Yunwen
Wu, Chengfeng
Zhou, Qinglin
Chandra, Rohitash
Artificial Intelligence
Large Language Models (LLMs) have shown impressive performance on a range of educational tasks, but are still understudied for their potential to solve mathematical problems. In this study, we compare three prominent LLMs, including GPT-4o, DeepSeek-V3, and Gemini-2.0, on three mathematics datasets of varying complexities (GSM8K, MATH500, and MIT Open Courseware datasets). We take a five-dimensional approach based on the Structured Chain-of-Thought (SCoT) framework to assess final answer correctness, step completeness, step validity, intermediate calculation accuracy, and problem comprehension. The results show that GPT-4o is the most stable and consistent in performance across all the datasets, but particularly it performs outstandingly in high-level questions of the MIT Open Courseware dataset. DeepSeek-V3 is competitively strong in well-structured domains such as optimisation, but suffers from fluctuations in accuracy in statistical inference tasks. Gemini-2.0 shows strong linguistic understanding and clarity in well-structured problems but performs poorly in multi-step reasoning and symbolic logic. Our error analysis reveals particular deficits in each model: GPT-4o is at times lacking in sufficient explanation or precision; DeepSeek-V3 leaves out intermediate steps; and Gemini-2.0 is less flexible in mathematical reasoning in higher dimensions.
title Evaluation of LLMs for mathematical problem solving
topic Artificial Intelligence
url https://arxiv.org/abs/2506.00309