Source item
Open original source ↗Interesting.
Quoted context
These are the quoted author’s words.
@DicksonPau @originalmagneto I've posted before that I prefer GPT-5.5 (xhigh) to Fable 5 for legal research, and I stand by that. I would never use Fable 5 for legal research over GPT-5.6 Sol. They're different weight categories, with all due respect to Fable 5. It's useful to remember what it means when I say that GPT-5.6 Sol Pro has saturated prinzbench. These are the hardest legal research questions I could think of, in my specialty area. Many involve tricks and/or require very painstaking research through a large volume of legal authorities. I doubt that there is more than a dozen practicing lawyers in my specialty area (of any seniority) who would be able to beat GPT-5.6 Sol Pro on my benchmark.
deredleritt3r ↗