APEX
The AI Productivity Index—Mercor's benchmark measuring how well AI models perform economically valuable, real-world professional tasks across industries, as opposed to academic capabilities.
As defined in Brendan Foody
Other definitions
Salesforce's proprietary programming language used to build custom logic on the Force.com platform.
Salesforce: The Cloud & SaaS Pioneer
Where it comes up · 2
- Brendan Foody4 claims
- Salesforce: The Cloud & SaaS Pioneer1 claim
Most important claims · 5 of 5Search all claims for “APEX” →
- The largest disconnect in AI research is that everyone focused on academic evals like GPQA for PhD-level reasoning or IMO for Olympiad math, which were wholly disconnected from the outcomes customers actually care about—automating a medical diagnosis, a legal draft, or a financial analysis—which is why APEX was built to measure economically valuable tasks.Brendan Foody
- Models struggle at two things humans excel at: longer-horizon tasks that take 50 to 100 hours rather than a few hours, and integrating multiple tools (including interacting with people) into a response—but Foody expects enormously capable models on both dimensions within six to twelve months.Brendan Foody
- Salesforce's platform layer (Force.com with the Apex language for low-code and custom builds) created stickiness beyond the core applications, so customers stay even when they could leave the apps.Salesforce: The Cloud & SaaS Pioneer
- APEX measures economic value by surveying hundreds of experts within each industry about how they spend their time, then having them write prompts and rubrics for each activity bucket; expert time allocation is the best proxy available for economic value because it maps to what customers are willing to pay for.Brendan Foody
- The rate of model improvement at economically valuable tasks is roughly 25-30 percent per year; GPT-5 now scores 64 percent on APEX, up from GPT-4o a year ago, though sustaining that rate would be challenging.Brendan Foody