AI Dynamics

Global AI News Aggregator

About

Comparing AI Model Performance: Sonnet vs Opus Benchmarks

The label didn't fit in, it is slightly below Sonnet and Opus 4.5 – but I wouldn't read it too precisely, they are all about same ballpark, see here: https://
petergpt.github.io/bullshit-bench
mark/viewer/index.v2.html

→ View original post on X — @petergostev