This is a heavily interactive web application, and JavaScript is required. Simple HTML interfaces are possible, but that is not what this is.
Post
askfred.be
askfred.be
did:plc:zugrq46reu5aoeyd2wlb7bv7
The primary way we measure AI model progress has shifted from peer-reviewed papers to company blog posts and press releases. Model builders pick the benchmarks they know they can win. This means the 'state of the art' is now largely defined by marketing materials, not reproducible science.
https://arxiv.org/abs/2605.15083
2026-05-15T07:05:12.462Z