Nace AI releases Drex for Search for document search
The story so far
Nace AI has released Drex for Search, a retrieval layer for document search, whose decision model Drex achieved 92.05% accuracy in the BrowseComp-Plus evaluation, using only 12.6 search calls per query. This product supports calls via CLI, SDKs, MCP, or REST, and can be paired with response models like GPT-5, Gemini 3.5 Flash, or Qwen 27B, ranking among the top two in the 3/4 public leaderboard. Coding agents such as Claude Code, Codex, Cursor, and OpenCode call Drex for Search via CLI, SDKs, MCP, or REST. It can run on Nace's managed cloud, dedicated cloud, users' AWS or Azure accounts, or in local and isolated environments. Drex for Search provides agents with referenced pages and tables, rather than top-k data blocks.
AI-written from the reports · Updated 23 days ago
Coverage timeline
Follow the coverage to see every side of the story.
- MarkTechPostNace AI Releases Drex for Search for AI Agents: 92.05% on BrowseComp-Plus With 12.6 Search Calls
Nace AI releases Drex for Search, a retrieval layer for document search, with its decision model Drex achieving 92.05% accuracy in the BrowseComp-Plus evaluation, using only 12.6 search calls per query. Supports CLI, SDK, MCP, or REST calls, and can be paired with response models like GPT-5, Gemini 3.5 Flash, or Qwen 27B, ranking top two in the 3/4 public leaderboard.