AI BriefingQUEST-35B Open-Sourced
Key point
A research team at Ohio State University has released QUEST-35B, a Deep Research agent trained using 32 H100 GPUs.
Details
The Ohio State University NLP research team has released QUEST-35B. This model was trained using approximately 32 H100 GPUs and 8,000 synthetic samples.
The research team open-sourced not only the model's weights but also the entire training recipe, code, and dataset, enhancing the reproducibility of the research. According to benchmark results, QUEST-35B shows competitive performance when compared with several existing frontier Deep Research systems.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.
Related
Whiteboard Launches Open-Source VS Code Fork for Human-AI Collaborative Software Design
OpenComputer Hosts 'Ship Video' Agent Using Claude Opus 5.5 to Generate Explainer Videos from Code