@kellogh ...indeed, also those benchmarks, i don't really trust them, let's see in practice when available (Claude 3 Opus) . Gemini was great in benchmarks too and i find pretty awful until now
@kellogh ...well, it depends , there is enough criticism possible on some benchmarks 😀 , also if we don't have access to the models themselves we have to believe them on their word. Regardless it looks like OpenAI has some more competition.
Add comment