Remix.run Logo
▲ Gemini 4 Neon looks like an Opus 5.5 competitor(micjm.com)
35 points by seizethecheese an hour ago | 6 comments
▲rootusrootus 6 minutes ago | parent | next [-]

I guess what I really want to know is how Gemini 4 Neon w/Antigravity compares with Opus 5.5/Claude Code. I'm not really into using LLMs in a particularly advanced way, I just use CC like 99% of the time when I need to write something, and then maybe Codex to second guess it.

But that's about as complicated as I get. I have recently tried to use Copilot because that is what work wants us to use, and even with Opus 5.5 it is noticeably inferior to CC on the same model. Wild. So clearly the harness matters.

▲seizethecheese a few seconds ago | parent [-]

[delayed]

▲quinndupont 12 minutes ago | parent | prev | next [-]

Fun analysis. I guess it’s not surprising to see the need for speed™ as an important factor, but who is using Fable for run of the mill coding work? It’s too pricey!

▲seizethecheese 5 minutes ago | parent [-]

Yeah, check out DeepSeek performance on the leaderboard. It wins ~half the time because it’s lightning fast and good enough.

▲afavour 16 minutes ago | parent | prev [-]

Looks like a good bunch of speculation in there but no bad news to be found. Just as good but cheaper? Sign me up.

For this model, I mean. And not the Anthropic IPO.

▲seizethecheese 13 minutes ago | parent [-]

Lots of speculation, yes.

Just as good but cheaper comes from the benchmark performance. Also faster from openrouter. The opus 5.5 parity projection is an internal model based on those assumptions from the Agent Duel team.