This model has the best score on that benchmark. Edit: Huh... It does score high... | Hacker News

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

		andai 57 days ago \| parent \| context \| favorite \| on: Gemini 3 Flash: Frontier intelligence built for sp... This model has the best score on that benchmark. Edit: Huh... It does score highest in "Omniscience", but also very high in Hallucination Rate (where higher score is worse)...

sabareesh 57 days ago [–]

this has one of the worse score in AA-Omniscience Hallucination Rate

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