Mistral AI reports Mistral Large 4 results on AutomationBench across 657 workflows

Mistral AI evaluated Mistral Large 4 on AutomationBench, testing 657 business workflows across simulated workplace applications including Gmail, Google Sheets, Slack, and Salesforce.

According to Mistral AI, Mistral Large 4 finished ahead of competing models including Kimi K3, MiMo-V2.6-Pro, and DeepSeek V4 Pro.