Benchmarking stalwarts Primate Labs on Thursday released Geekbench AI 1.0. The app, which is currently available for Android, Linux, MacOS and Windows, applies Geekbench’s principles to machine learning, deep learning and other AI workloads, in a bid to standardize performance ratings across platforms. It’s a successor to Geekbench ML (machine learning), which was announced in 2021 and is currently on version 0.6.
“[I]n recent years, companies have coalesced around using the term ‘AI’ in these kinds of workloads (and in their related marketing),” Primate Labs says of the name change. “To ensure that everyone, from engineers to performance enthusiasts, understands what this benchmark does and how it works, we felt it was time for an update.”
Earlier this week, ChatGPT-maker OpenAI announced a new version of its own AI model benchmark. SWE-bench Verified is a “human-validated” offering that uses human validation to determine models’ efficacy in solving “real-world issues.”
Source : Techcrunch
