Model choice involves cost and task accuracy

Wade Foster says the leading model on Zapier’s Automation Bench completed about 40% of its automation tasks accurately. He describes cheaper models as costing less while performing reasonably well, and argues that organizations should be able to choose models for different workflows.

Wade Foster·Publié 17 sept. 2026

Derrière ce point de vue

Les traductions sont destinées à la lecture ; les extraits originaux restent la source evidence.

No Code Is Code: Zapier CEO Wade Foster on Headless Tools, Zapier MCP & Automation Bench

Extrait original

It performs about 40% of the tasks accurately, which is the highest that there is. Now, it's more expensive than, say, something like Gemini 3.7, which is, does pretty good but does it at a fraction of the cost.

Cet extrait ne contient pas de contexte supplémentaire. Consultez la conversation originale.

Ouvrir l’original · 10:21 Voir la page source

L’heure de début provient de la transcription fournie. L’alignement avec la lecture est en attente de révision.