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

Mistral AI shared evaluation results on AutomationBench, where Mistral Large 4 completed 657 business workflows across simulated workplace applications and finished ahead of Kimi K3, MiMo-V2.6-Pro, and DeepSeek V4 Pro.

Language: en
Time zone: America/Los_Angeles

HTML: https://didcodexreset.com/news/2ac55c89f47a4e05a81a8484.html

Content language: en
Localization state: sameLanguage

Source: Mistral AI · Published 10/7/2026, 07:33:03

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.

Tags: Mistral AI, Mistral Large 4, Benchmarks

[View original post](https://x.com/MistralAI/status/2107834895674323354)