from Hacker News

SOTA Model in 8B Size?

by ConteMascetti71 on 5/29/25, 1:19 PM with 2 comments

  • by ConteMascetti71 on 5/29/25, 1:20 PM

    I think it's not possible to have the same knowledge capabilities of greater models...but.... reasoning?
  • by ConteMascetti71 on 5/29/25, 1:19 PM

    ..we distilled the chain-of-thought from DeepSeek-R1-0528 to post-train Qwen3 8B Base, obtaining DeepSeek-R1-0528-Qwen3-8B. This model achieves state-of-the-art (SOTA) performance among open-source models on the AIME 2024, surpassing Qwen3 8B by +10.0% and matching the performance of Qwen3-235B-thinking