Skip to content

CoWorkBench

Qwen's internal benchmark for long-horizon professional work across computer science, finance, law, medicine, and other productivity domains.

4 models

Higher is better.

  1. 1Qwen3.8-Omni-FlashAlibaba75.3
  2. 2Qwen3.8 MaxAlibaba74.8
  3. 3Qwen3.8-Flash-NextAlibaba73.9
  4. 4Qwen3.8-27BAlibaba70.7
Higher is better. Bar colour: blue proprietary, orange open weights, green other.

About this benchmark

Metric
Provider-run agent score
Tasks
Long-horizon professional workflows
Authors
Qwen Team (2026)

Scores are as reported by model developers or evaluators and may use different settings (for example reasoning effort or tools). Compare with care.