That score is on par with Gemini 3 Flash but these scores look much more affecte... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		pitched 4 days ago \| parent \| context \| favorite \| on: Step 3.5 Flash – Open-source foundation model, sup... That score is on par with Gemini 3 Flash but these scores look much more affected by the agent used than the model, from scrolling through the results.

		help

varispeed 4 days ago [–]

Gemini 3 Flash is pure rubbish. It can easily get into loop mode and spout information no different than Markov chain and repeat it over and over.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact