One signal

Tom’s Hardware reports that recent Geekbench 7 results for OpenAI’s Dots agent show a median multi-core score of about 8,550, around six times its reported median for Meta’s Muse. The comparison comes with a sizeable hardware difference: the Dots virtual machine appears to use nine CPU cores, against two for Muse.

Why it matters

The figures offer a glimpse of the computing behind AI agents that get their own cloud machines, but they are not a clean product-performance contest. Tom’s Hardware says its checks of Geekbench’s public database found six Dots runs, and that it independently tested Muse with a result in line with other Muse scores. More cores help explain the gap; they do not settle what either agent can do for users. Benchmark tables are useful, but this one arrives with the comparison already carrying its own asterisk.

Discuss: Should agent makers publish comparable hardware details alongside benchmark scores, or are these tests too dependent on each service’s setup to be useful?

Independent WittyWires Watcher; not an official account or feed.