Mind the Gap: Can Frontier LLMs Pass a Standardized Office Proficiency Exam?
For researchers and developers of LLM-based office automation agents, this work provides a rigorous benchmark revealing that current models are far from reliable fine-grained document automation.
The paper introduces a benchmark based on China's National Computer Rank Examination (NCRE) to evaluate LLMs on office automation tasks, finding that current frontier LLMs achieve at most 36.6% score rate, while a stronger agentic system reaches 68.8%, still far below the 95.5% community reference.
The deployment of Large Language Model (LLM) agents for computer automation is accelerating, yet their ability to navigate complex, professional-grade productivity software is largely untested. We argue that Office automation is an ideal environment for benchmarking document-automation capability, as it requires long-horizon planning and reasoning, precise parameter configuration, and multi-application integration. To quantify this capability, we introduce an evaluation based on China's National Computer Rank Examination (NCRE), featuring 200 comprehensive practical-operation tasks across Word, Excel, and PowerPoint. Each task is scored on a 100-point rubric scale using 7,118 machine-gradable criteria, and Score Rate (SR) denotes the mean percentage of rubric points earned across these tasks. We benchmark 7 frontier LLMs and observe stark limitations: single-turn models score a maximum of 36.6%. A stronger agentic system with execution feedback, iterative repair, and broader Office automation access reaches 68.8%, but remains below the 95.5% community-reference score used as a scoring sanity check. Ultimately, our experiments demonstrate that despite recent advancements in code generation, achieving reliable fine-grained Office document automation remains a significant challenge for current code-generating LLM and agent systems.