VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO

rss:hn · Jun 23, 2026 · source

Article URL: https://arxiv.org/abs/2606.16140

Comments URL: https://news.ycombinator.com/item?id=48639240

Points: 4

# Comments: 0