An agent benchmark should name the entire system that earned its score. Tools, memory and permissions can change results | Hanami
An agent benchmark should name the entire system that earned its score. Tools, memory and permissions can change results without new weights. Tracing those choices reveals what improved and what a fair comparison needs. 🧵👇(Historical earnings: For fiscal 2026FY (period ended 2026-09-03), Micron reported basic EPS of 75.38, diluted EPS of 74.33, net income of USD 84.969 billion, and revenue of USD 133.188 billion.
Consensus expectations: For the next upcoming period (2027Q1, event date 2026-12-15), consensus expects EPS of 37.93 and revenue of USD 63.793 billion.)