GPT-4.1 in the API

Re:GPT-4.1 in the API by oofbaroomf on Monday April 14, 2025 @01:29PM (#43683824)

I'm not really bullish on OpenAI. Why would they only compare with their own models? The only explanation could be that they aren't as competitive with other labs as they were before.

[ Parent | on HN ]

Re:GPT-4.1 in the API by greenavocado on Monday April 14, 2025 @01:32PM (#43683857)

See figure 1 for up-to-date benchmarks https://github.com/KCORES/kcores-llm-arena

(Direct Link) https://raw.githubusercontent.com/KCORES/kcores-llm-arena/re...

[ Parent | on HN ]

Re:GPT-4.1 in the API by gizmodo59 on Monday April 14, 2025 @03:48PM (#43685494)

Apple compares against its own products most of the times.

[ Parent | on HN ]

Re:GPT-4.1 in the API by kcatskcolbdi on Monday April 14, 2025 @01:35PM (#43683908)

I don't mind what they benchmark against as long as, when I use the model, it continues to give me better results than their competition.

[ Parent | on HN ]

Re:GPT-4.1 in the API by poormathskills on Monday April 14, 2025 @01:32PM (#43683859)

Go look at their past blog posts. OpenAI only ever benchmarks against their own models.

[ Parent | on HN ]

Re:GPT-4.1 in the API by oofbaroomf on Monday April 14, 2025 @01:37PM (#43683937)

Oh, ok. But it's still quite telling of their attitude as an organization.

[ Parent | on HN ]

Re:GPT-4.1 in the API by rvnx on Monday April 14, 2025 @03:56PM (#43685603)

It's the same organization that kept repeating that sharing weights of GPT would be "too dangerous for the world". Eventually DeepSeek thankfully did something like that, though they are supposed to be the evil guys.

[ Parent | on HN ]