Gemini 3.7 Flash Tops Zapier's AutomationBench, Beating Pricier Claude and GPT Models

_philschmid · x · 2026-08-14

Zapier's AutomationBench evaluates LLMs on end-to-end workflow execution using 47 real tools across six business functions: Sales, Marketing, Operations, Support, Finance, and HR.

Gemini 3.7 Flash ranks 1st with a 30.44% success rate and a cost of $0.61 per task, outperforming more expensive models like Claude Opus 5 and GPT-5.6 Terra. It dominates in Marketing, Finance, Sales, and Support, but trails behind Claude Opus 5 in Operations.

Original post →

More from coding & agent

coding & agent channel →