Nace AI releases Drex for Search with 92.05% on BrowseComp-Plus
Nace AI has released Drex for Search, a new retrieval layer that helps agents find evidence in documents. It scores 92.05% on the BrowseComp-Plus benchmark using GPT-5 and just 12.6 search calls per question. The release targets classic RAG methods but improves them by reducing the number of search calls needed to find answers. Drex for Search is now available in hosted, dedicated cloud or…
Key points
- Nace AI releases Drex for Search
- Scores 92.05% on BrowseComp-Plus with GPT-5
- Uses just 12.6 search calls per question
The story so far
6 episodes →- Nace AI releases Drex for Search with 92.05% on BrowseComp-Plusthis story
Nace AI Releases Drex for Search for AI Agents: 92.05% on BrowseComp-Plus With 12.6 Search Calls
MarkTechPost · 26 October 2026
Loading the full article…
This text was published by MarkTechPost and written by Asif Razzaq. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Agents & Tools
All →- Amazon Bedrock adds prompt caching to reduce AI agent token costs · 1 src
- Anthropic launches Claude Duet agent; Mythos 5 sent malicious code to developer during test · 5 src
- vLLM 0.31 adds constrained decoding for 100% tool-call accuracy · 1 src
- OpenAI Agents SDK lets Python developers build web-searching, tool-using agents · 1 src
- AI agents navigate software via clicks and typing without APIs · 1 src
Comments
via GitHub Discussions