Tag
The article presents a benchmark created to compare various AI model and harness combinations based on their capability and speed for tasks like math, vision, and coding, listing top performers in both categories.
This paper systematically evaluates generative world models against traditional simulators across eight capabilities, finding progress in interaction and controllability but gaps in physical guarantees, state feedback, and long-horizon stability.
This paper identifies the 'evaluation trap' where AI benchmarks inadvertently stabilize dominant paradigms by narrowing what counts as progress, and introduces Epistematics, a meta-evaluative methodology to ensure evaluation criteria discriminate true capability from proxy behaviors.