Skip to content
Read the original: Mistral AI· Published 22/100AI score22/100

Mistral Large 4 tops AutomationBench, ahead of Kimi K3 and DeepSeek V4 Pro

Original titleGmail. Google Sheets. Slack. Salesforce.

AISummary

Mistral Large 4 scored highest on AutomationBench, a benchmark of 657 business workflows across simulated workplace apps including Gmail, Google Sheets, Slack, and Salesforce. It finished ahead of Kimi K3, MiMo-V2.6-Pro, and DeepSeek V4 Pro.

Read the original x.com

Source: Mistral AI · x.comPublished · added here

AI agentsOpen-source ecosystemEvals & benchmarks#Eval/Benchmark#Agent