OpenAI o3 and o4-mini • Hacker News Board

Re: OpenAI o3 and o4-mini

#11

Post by zvitiate » Wed, Apr 16, 2025, 5:14 PM UTC

morkalork wrote: post #9

If the ai is smart, why not have it choose the model for the user

That’s what GPT-5 was supposed to be (instead of a new base or reasoning model) last Sam updated his plans I thought. Did those change again?

Re: OpenAI o3 and o4-mini

#12

Post by originalvichy » Wed, Apr 16, 2025, 5:15 PM UTC

Is there a non-obvious reason using something like Python to solve queries requiring calculations was not used from day one with LLMs?

Re: OpenAI o3 and o4-mini

#13

Post by ksylvest » Wed, Apr 16, 2025, 5:15 PM UTC

Are these available via the API? I'm getting back 'model_not_found' when testing.

Re: OpenAI o3 and o4-mini

#14

Post by planb » Wed, Apr 16, 2025, 5:15 PM UTC

What is wrong with OpenAI? The naming of their models seems like it is intentionally confusing - maybe to distract from lack of progress? Honestly, I have no idea which model to use for simply everyday tasks anymore.

Re: OpenAI o3 and o4-mini

#15

Post by falleng0d » Wed, Apr 16, 2025, 5:15 PM UTC

Maybe they should ask the new models to generate a better name for themselves. It's getting quite confusing.

Re: OpenAI o3 and o4-mini

#16

Post by gallerdude » Wed, Apr 16, 2025, 5:16 PM UTC

brap wrote: post #4

Where's the comparison with Gemini 2.5 Pro?

For coding, I like the Aider polyglot benchmark, since it covers multiple programming languages.

Gemini 2.5 Pro got 72.9%

o3 high gets 81.3%, o4-mini high gets 68.9%

Re: OpenAI o3 and o4-mini

#17

Post by maheshrijal » Wed, Apr 16, 2025, 5:16 PM UTC

firejake308 wrote: post #10

Not sure what the goal is with Codex CLI. It's not running a local LLM right, just a CLI to make API calls from the terminal?

This might be their answer to claude code more than anything else.

Re: OpenAI o3 and o4-mini

#18

Post by sho_hn » Wed, Apr 16, 2025, 5:16 PM UTC

typs wrote: post #8

I’m not sure I fully understand the rationale of having newer mini versions (eg o3-mini, o4-mini) when previous thinking models (eg o1) and smart non-thinking models (eg gpt-4.1) exist. Does anyone here use these for anything?

I use o3-mini-high in Aider, where I want a model to employ reasoning but not put up with the latency of the non-mini o1.

Re: OpenAI o3 and o4-mini

#19

Post by planb » Wed, Apr 16, 2025, 5:16 PM UTC

originalvichy wrote: post #12

Is there a non-obvious reason using something like Python to solve queries requiring calculations was not used from day one with LLMs?

Because it‘s not a feature of the LLM but the product that is built around it (like ChatGPT).

Re: OpenAI o3 and o4-mini

#20

Post by zapnuk » Wed, Apr 16, 2025, 5:16 PM UTC

Surprisingly, they didn't provide a comparison to Sonnet 3.7 or Gemini Pro 2.5—probably because, while both are impressive, they're only slightly better by comparison.

Lets see what the pricing looks like.