Oh boy, if the benchmarks are this good and Opus feels like it usually does then this is insane.
I’ve always found Opus significantly better than the benchmarks suggested.
LFG
Claude Opus 4.5
31–40 of 525 posts
Re: Claude Opus 4.5
#32The real question I have after seeing the usage rug being pulled is what this costs and how usable this ACTUALLY is with a Claude Max 20x subscription. In practice, Opus is basically unusable by anyone paying enterprise-prices. And the modification of "usage" quotas has made the platform fundamentally unstable, and honestly, it left me personally feeling like I was cheated by Anthropic...
Re: Claude Opus 4.5
#33I've played around with Gemini 3 Pro in Cursor, and honestly: I find it to be significantly worse than Sonnet 4.5. I've also had some problems that only Claude Code has been able to really solve; Sonnet 4.5 in there consistently performs better than Sonnet 4.5 anywhere else. I think Anthropic is making the right decisions with their models. Given that software engineering is probably one of the very few domains of AI…
I have heard that gemini 3 is not that great in cursor, but excellent in Antigravity. I don't have a time to personally verify all that though.
Nothing is great in Cursor.
Re: Claude Opus 4.5
#34Re: Claude Opus 4.5
#35I've played around with Gemini 3 Pro in Cursor, and honestly: I find it to be significantly worse than Sonnet 4.5. I've also had some problems that only Claude Code has been able to really solve; Sonnet 4.5 in there consistently performs better than Sonnet 4.5 anywhere else. I think Anthropic is making the right decisions with their models. Given that software engineering is probably one of the very few domains of AI…
My testing of Gemini 3 Pro in Cursor yielded mixed results. Sometimes it's phenomenal. At other times I either get the "provider overloaded" message (after like 5 mins or whatever the timeout is), or the model's internal monologue starts spilling out to the chat window, which becomes really messy and unreadable. It'll do things like:
>> I'll execute.
>> I'll execute.
>> Wait, what if...?
>> I'll execute.
Suffice it to say I've switched back to Sonnet as my daily driver. Excited to give Opus a try.
Re: Claude Opus 4.5
#36I've played around with Gemini 3 Pro in Cursor, and honestly: I find it to be significantly worse than Sonnet 4.5. I've also had some problems that only Claude Code has been able to really solve; Sonnet 4.5 in there consistently performs better than Sonnet 4.5 anywhere else. I think Anthropic is making the right decisions with their models. Given that software engineering is probably one of the very few domains of AI…
My workflow was usually to use Gemini 2.5 Pro (now 3.0) for high-level architecture and design. Then I would take the finished "spec" and have Sonnet 4.5 perform the actual implementation.
Re: Claude Opus 4.5
#37Earlier quoted context omitted.
I suspect Cursor is not the right platform to write code on. IMO, humans are lazy and would never code on Cursor. They default to code generation via prompt which is sub-optimal.
> They default to writing code via prompt generation which is sub-optimal. What do you mean?
If you're given a finite context window, what's the most efficient token to present for a programming task? sloppy prompts or actual code (using it with autocomplete)
Re: Claude Opus 4.5
#38I've played around with Gemini 3 Pro in Cursor, and honestly: I find it to be significantly worse than Sonnet 4.5. I've also had some problems that only Claude Code has been able to really solve; Sonnet 4.5 in there consistently performs better than Sonnet 4.5 anywhere else. I think Anthropic is making the right decisions with their models. Given that software engineering is probably one of the very few domains of AI…
I have heard that gemini 3 is not that great in cursor, but excellent in Antigravity. I don't have a time to personally verify all that though.
My first couple of attempts at antigravity / Gemini were pretty bad - the model kept aborting and it was relatively helpless at tools compared to Claude (although I have a lot more experience tuning Claude to be fair). Seems like there are some good ideas in antigravity but it’s more like an alpha than a product.
Re: Claude Opus 4.5
#39The first chart is straight from "how to lie in charts"..
Re: Claude Opus 4.5
#40Why do they always cut off 70% of the y-axis? Sure it exaggerates the differences, but... it exaggerates the differences.
And they left Haiku out of most of the comparisons! That's the most interesting model for me. Because for some tasks it's fine. And it's still not clear to me which ones those are.
Because in my experience, Haiku sits at this weird middle point where, if you have a well defined task, you can use a smaller/faster/cheaper model than Haiku, and if you don't, then you need to reach for a bigger/slower/costlier model than Haiku.