Huh I guess all the benchmarks are wrong then | Hacker News

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

		mountainriver on July 16, 2024 \| parent \| context \| favorite \| on: Codestral Mamba Huh I guess all the benchmarks are wrong then

GaggiX on July 17, 2024 | [–]

3.5 Sonnet outperforms GPT-4o on most benchmarks.

causal on July 16, 2024 | [–]

Agreed.

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