CoWorkBench

reasoning

Multilingual: no

CoWorkBench is Qwen's internal cowork benchmark for evaluating long-horizon office and productivity agent tasks across domains such as computer science, finance, law, and medicine.

Methodology

Imported from llm-stats public benchmark metadata. Modality: text. Max score: 1. Categories: agents, productivity, reasoning. Language: en. Verified by llm-stats: no.