AutomationBench: Gemini 4 Carbon hits 53.9%, beating Argon's 51.3%
Carbon reaches 53.9% on AutomationBench four weeks after Argon's 51.3%, with finance jumping to 60%, and Medium effort at about $1.65 per task already beats Argon on High.
Google just beat its own record on our AutomationBench. Carbon hit 53.9%, just 4 weeks after their Argon model scored 51.3%. Big month for @GoogleDeepMind and @OfficialLoganK. Carbon's biggest gain over Argon is Finance (60%, up from 48%). It's also super strong for Operations (68%) and Marketing (64%). It's weaker for Support (46%), and Argon still leads on HR. I'd recommend running Carbon on Medium effort. Medium scored 53.0%, about the same as High, for about $1.65 a task. Even at Medium, Carbon beats Argon on High (51.3%) at about the same price ($1.70 a task). Each lab has shipped different models for different jobs. If you run just one model (or lab) across the whole company, you're leaving points on the table somewhere. Use any AI with @Zapier, and use Zapier anywhere you build with AI.