have tested it with the usual suspects... 4o is 👌 and sonnet 3.7 pretty good; gemini got confused and didn't finish; grok 3 said it was too difficult and eventually did a simplified analysis; r1's analysis was mid and misquoted things; and i had a long discussion of refusals w…
oh also r1 much better when i pasted the transcript into the message rather than using pdf of screenshot