Evaluating the Sufficiency of Single-Agent LLM Systems for Algorithmic Problem Solving in Support and Operations
收藏Zenodo2026-03-30 更新2026-05-26 收录
下载链接：
https://zenodo.org/doi/10.5281/zenodo.17751554
下载链接
链接失效反馈官方服务：
资源简介：
This dataset includes all raw data of a research that use four state-of-the-art LLMs (GPT-5.1, Claude-4.5, Deepseek-chat-v3.1, and Gemini-2.5-pro) on a dataset of 150 self-contained algorithmic problems (50 Easy, 50 Medium, 50 Hard extracted from LeetCode).
提供机构：
Zenodo
创建时间：
2025-11-28
