Another long-horizon benchmark, another reminder that current AI can work for hours and still remain far from mastering the task. The strongest agent in EdgeBench scored 51.3/100 after being allowed to work for 12 hours. The benchmark gives agents persistent executable environments and feedback across 134 tasks. They can debug code, run simulations, inspect validation results, revise proofs, and repeatedly submit artifacts to hidden judges. i.e. they had many of the ingredients we normally say agents need to improve over time. They still struggle to convert all of that interaction into sustained progress. The study covers roughly 38,000 hours of interaction across 6 task families. When performance was averaged across tasks, improvement followed a log-sigmoid curve with R² ≥ 0.997 across all 5 models: slow early progress, a steeper learning phase, then saturation.