Against GPT3.5 perhaps the gaps aren’t too big for your use cases, but I wouldn’t say it’s in the GPT4 league. It looks close in the benchmarks but the difference in quality feels (to me) huge in practice. The others models are simply a lot worse.
Interesting. Have you tried StableVicuna?
No, is it worth a try? I didn’t see a lot of hype about it so I didn’t try it.