I can believe this, Deepseek V3.2 shows that you can get close to "gpt-5" perfor... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		krackers 16 days ago \| parent \| context \| favorite \| on: OpenAI declares 'code red' as Google catches up in... I can believe this, Deepseek V3.2 shows that you can get close to "gpt-5" performance with a gpt-4 level base model just with sufficient post-training.

irthomasthomas 16 days ago [–]

Deepseek scores Gold at IMO and IOI while GPT-5 scores Bronze. OpenAI now has to catch up to china.

arcanemachiner 16 days ago | [–]

...in a single benchmark.

irthomasthomas 16 days ago | | [–]

No. Many benchmarks, I just mentioned those two as they where being bragged about by openai and Google when their internal models achieved gold.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact