Ask HN: What's the latest concensus on OpenAI vs. Anthropic $20/month tier?

[whatarethembits]

I'm considering $20/month variants only.

I've had a Claude subscription for the past year, although I only really started properly using LLMs in the past couple of months. With Opus, I get about 5 messages every 5 hours (fairly small codebase); more with Sonnet. I then cancelled that, since its practically unusable and got ChatGPT sub about a week ago. Currently using it with 5.4 High and I haven't had to worry about limits. But the code it produces is definitely "different" and I need to plan more in advance. Its plan mode is also not as precise as with Claude (it doesn't lay out method stubs it plans to implement etc) so I suppose I may need to change how I work with it? Lastly, for normal chats it produces significantly more verbose output (with personality set to Efficient) and fast (with Thinking) but often it feels as though its not as thorough as I'd like it to be.

My question; is this a "you're holding it wrong" type of situation, where I just need to get used to a different mode of interaction? Or are others noticing material difference in quality? Ideally I'd like to stick with ChatGPT due to borderline impractical limits with Anthropic.

[Areena_28]

I know with Claude, hitting 5 messages every 5 hours mid-task is a real workflow problem.

Many times, when i used to hit claude limits mid task and switched to ChatGPT thinking the no-limit thing would make up for it. But it's really annoying.

I ended up just being more deliberate about how i use Claude. longer more complete prompts instead of back and forth, which naturally stretches the messages further. not a perfect fix but it changed the experience enough to stick with it.

[kasey_junk]

I think it really depends on how fully formed you ai workflows are. I have a very opinionated set of skills and agents files and a harness for running prompts against both for code production.

I do head to head comparisons with this setup pretty regularly and what I’ve found is there is not much difference in outcomes between the 2 frontier labs at equivalent model settings. It’s hard to get statistically significant results on my budget and eval ability but my anecdotal feeling is that there is as much difference in group as out in outcomes.

Given that setup I use codex much more than Claude because it’s more reliable.

But I believe it’s easier to go from nothing to decent with Claude.

For other stuff I use Claude.

[khaledh]

I use both at the same time:

- Claude Opus for general discussion, design, reviews, etc.

- Codex GPT-5.4 High for task breakdown and implementation.

I often feed their responses to each other (manual copy/paste) to validate/improve the design and/or implementation. The outcome has been better than using one alone.

This workflow keeps Claude's usage in check (it doesn't eat as much tokens), and leverages Codex generous usage limits. Although sometimes I run into Codex's weekly limit and I need to purchase additional credits: 1000 credits for $40, which last for another 4-5 days (which usually overlap with my weekly refresh, so not all the credits are used up).

[01jonny01]

Claude is good for producing 1 shot polished apps, but you will quickly burn through your allowance.

Chatgpt needs more prompting to get what you want, but its nearly impossible to reach your limit.

[skyberrys]

I have the same experience with Claude, but it's been rare for me to hit limits. I tend to ask it one or two improvements to the app and then I have a time burden of using the app to make sure it's still what I intended. I have the $200 per year plan which I think is the same as $20 per month just I paid in bulk for a discount.

[01jonny01]

I get it to do my testing for me aswell.

[skyberrys]

That's a great idea! I'll try it out, it might save me a lot of time. I haven't really done user testing before, how do you test for things like 'still feels responsive ' and 'is easy to use one handed'? I'm currently running with 0 programmed tests but I do spend like 4+ hours just using the app between Claude sessions.

[01jonny01]

I write my goals. Claude drafts a plan. I then feed it to Claude Chrome extension for live testing. Claude Chrome extension will set up the console inspector, measure response times and change UA if it's part of the plan. I'm sure you could tell Claude Chrome extension "ok make this change on the fly" by injecting JS into the console and do AB testing and output the result in an easy to understand report.

[2020science]

My experience is that it all comes down to personal fit and feel. I switched from ChatGPT to Clause several months ago and much prefer it - although do get frustrated at glitches and hitting limits. But I'm a writer and academic, and the LLM fits my purpose better. With what I do ChatGPT does nott feel great to use.

[jaysethi]

I find Claude to be more opinionated. Their heavy focus on alignment really helps it embody a personality. More of this in their [system card](https://www-cdn.anthropic.com/6d8a8055020700718b0c49369f6081...)

[yo103jg]

My current split: Claude for code, Gemini for harder reasoning, ChatGPT for more structured output.

ChatGPT is still useful, but mostly for tasks where formatting, organization, and response shape matter. If I’m judging mostly on raw capability, probably rank Gemini above it.

[pcael]

Have you tried Claude console client?

[whatarethembits]

Do you mean Claude Code? If so, that's what I use(d) primarily for development, and Claude Desktop for general chats. My issue with Opus was that, every time I start a new task in Plan mode, it'd use 50k - 100k tokens and that'd by about 20% of the session limit. A bit of back and forth and its done for most of the work day. Just not feasible at all. The tasks I wanted it to perform were fairly small and contained, "Look at these three files @@@ and add xxx to @file. DON'T read any other files. If you need more context, ask me.". That worked sometimes but not always, still burned a lot of tokens.

[pcael]

Yes I meant Claude Code client. Indeed Opus is a token eater, I usually use Sonnet because or that.

[calcpocket]

Honestly, I am not very satisfied with ChatGPT. It might be good for some things but lacks in other. I am not saying the Claude is much better, but if I chose to pay for one of them if would be Claude.