Research·EASYHUB JOURNAL
OpenThinker-32B shares reasoning weights and training data
What changed
The OpenThoughts effort shares a reasoning model, training data and generation pipeline. Reported benchmark results concern a specific setup; the open assets make data choices and subsequent experiments more inspectable.
- Original title
- 直逼 DeepSeek-R1-32B，UC 伯克利等开源全新 SOTA 推理模型 OpenThinker-32B
- Source
- 新智元 · www.ithome.com
- Author or account
- 新智元（ID：AI_era）
- Topic
- Research
- Source month
- 2025-02
This is a concise EasyHub summary of the linked source, not the full report or original reporting. Availability and preview conditions are described in the summary and original.
Summary page published · Editorial information