Nace AI releases Drex for Search for AI agents: 92.05% on BrowseComp-Plus with 12.6 search calls. October 26, 2026 Nace AI has released Drex for Search, which brings its Drex decision models to document search. Drex for Search is a retrieval layer that helps people and agents find evidence. Coding agents such as Claude Code, Codex, Cursor and OpenCode call it through CLI, SDKs, MCP or REST. In Nace's evaluation, it scores 92.05% on BrowseComp-Plus with GPT-5, using 12.6 search calls per question. Tl;dr. * Size: a hosted search system built to search over 1M+ files. It pairs with an answering model such as GPT-5, Gemini 3.5 Flash or Qwen 27B. * Runs on: Nace's managed cloud, a dedicated cloud, your own AWS or Azure account, or on-prem and air-gapped. * Performance: ranked #1 or #2 on 3 of 4 public leaderboards, per Nace. * Best: 77.5% R@1 on VisDocAgentBench, 10 points above Claude Opus 5 (67.5%). What did Nace AI release? Nace AI frames search as a series of decisions. Drex for Search applies its Drex models to those decisions. Drex scores given options with a calibrated probability each, in 1 forward pass. That makes it cheap enough for every agent step. The release targets classic RAG, which Nace sums up as chunk, embed, top-k, hope. The pipeline breaks in 3 cases: * the answer sits in a table on page 23 * the answer needs 2 hops across files * the answer is inside a scanned PDF How does Drex for Search work inside an agent? Nace describes 3 steps: * Classify: Before any search runs, Drex decides if the question needs a quick lookup or an agent. The agent route reads documents and queries tables. * Squeeze: Drex walks the workspace level by level: folder, file, section, page. Inside a sheet, it narrows to table and column. Each level keeps only what can hold the answer. * Answer: Only the kept pages and tables reach the LLM. The answer cites the file and page. Depth is fixed, so Nace says a million files take as many steps as a thousand. How much does it help coding agents? Nace AI tested 9 agent and model pairs on OfficeQA Pro, a 133-question benchmark over U.S. Treasury Bulletins. Key highlights: 6% more answers right, 62% fewer steps, 56% fewer tokens, and 2.3x faster. What does a workspace include? * Files: PDFs and scans, xlsx, csv and Parquet, mp3 and mp4, docx, pptx, md, json and txt. * Citations: every answer names the file and the page, row or minute it came from. * Workspaces: isolated, with their own index and knowledge graph, and shareable with invited members. * Storage: upload files or folders, or keep workspaces in your own S3 bucket or Azure Blob container. * Zero retention: available with your own storage. * Domains: Tax, M&A, SEC 10-K, Contracts, or your own. How does it perform on BrowseComp-Plus? BrowseComp-Plus asks a deep-research agent 830 multi-hop questions over about 100K fixed web documents. With GPT-5, Nace AI reports: * 92.05% accuracy, #2 of 86 entries on the leaderboard. * 12.61 search calls per question, 16.6x fewer than the only entry ahead (209.27 calls). * 87.32% in a single pass with 8.93 search calls, the best of any entry under 10 calls. * +20.4 points over the Qwen3-Embed-8B baseline, with the same GPT-5 model. How does it score on document benchmarks? On VisDocAgentBench, an agent finds 1 target page among 2,375 arXiv pages. Drex for Search scores 77.5% R@1 with an open-weight Qwen 27B planner. The best published agent, Claude Opus 5, scores 67.5%. R@1 is 97.5% on direct questions, 77.5% on one bridge, and 57.5% on two. On MADQA, agents answer over 800 PDFs and cite pages. Nace reports 94.7% accuracy with Gemini 3.5 Flash and a page-attribution F1 of 88.2. Its effort calibration (Kuiper) is 6.66. Nace ranks it #1, based on the leaderboard as read on October 20. With open-weight Qwen 27B, Nace reports 93.4%. On EnterpriseRAG-Bench, with 500,000+ internal company documents, Nace reports an overall score of 88.22, which it ranks #3. That is 27.2 points above OpenAI File Search (61.03). How does it compare with the best published results? Ranks and scores are as published by Nace AI, from leaderboards read October 20, 2026. How can developers get access? Drex for Search runs in the Nace API Console, with 4 ways in on one key: * CLI: nace-cli on PyPI. * SDKs: nace-sdk for Python and nace-sdk for TypeScript. * MCP: nace-mcp, for Claude Code, Codex, Cursor or OpenCode. * REST: an OpenAPI spec. Key takeaways. * Drex for Search gives agents cited pages and tables, not top-k chunks. * 92.05% on BrowseComp-Plus with 16.6x fewer search calls than the only entry ahead. * 77.5% R@1 on VisDocAgentBench, 10 points above Claude Opus 5. * On OfficeQA Pro, agent turns fell for all 9 harness and model pairs Nace tested. [Thanks to the Nace AI team for the thought leadership / resources for this article. This article is sponsored by Nace AI.] Asif Razzaq is the CEO of Marktechpost AI Media Inc... As a visionary entrepreneur and engineer, Asif is committed to harnessing the potential of Artificial Intelligence for social good. His most recent endeavor is the launch of an Artificial Intelligence Media Platform, Marktechpost, which stands out for its in-depth coverage of machine learning and deep learning news that is both technically sound and easily understandable by a wide audience. The platform boasts of over 2 million monthly views, illustrating its popularity among audiences.

Introducing Drex Max, a multimodal decision model for computer use. Drex Max, a decision model that sees the screen Generally available. First among decision models on the public Decision Index 0.3.2, and it reads text, images and video. A computer-use agent spends most of its time on small decisions. Which button to click. Which field to fill. Which search result to open. Whether the page has finished loading. A single task can take thirty of them, and today each one usually means sending a screenshot to a large frontier model and waiting seconds while it writes an answer. Today Nace.AI is releasing Drex Max. It is its most capable decision model, and the first one that sees. You give it a screenshot, a screencast, a scanned document, a chart or a photo, along with a set of typed questions, and one forward pass returns a probability for every option you supplied. Drex Max is built to sit inside that loop and make each of those small decisions in milliseconds, at a fraction of what a frontier model costs. Benchmarks. Decision models benchmark. | Benchmark | Drex Max | Drex v2.0 | Drex v1.5 | Jev 1.14 | GPT-6 Luna Decisions | GPT-6 Sol | Claude Opus 5.5 | | Decision benchmarks | / | / | / | / | / | / | / | | Decision Index (public) | 67.6 | 61.3 | 58.1 | 60.7 | 47.8 | - | - | | JevBench | 92.2 | 85.7 | 84.8 | 86.7 | 91.0 | 99.1 | 100.0 | | Decision Bench | 94.3 | 88.3 | 86.8 | 92.3 | 90.5 | 94.7 | 95.6 | | DecideBench (item) | 98.5 | 96.5 | 90.0 | 98.0 | 97.2 | 99.2 | 98.8 | | DecideBench (pair) | 97.0 | 93.5 | 80.5 | 96.0 | 94.5 | 98.5 | 98.5 | | Game Bench (win %) | 64.0 | 60.3 | 58.7 | 50.0 | 57.5 | 65.0 | 63.0 | | Knowledge | / | / | / | / | / | / | / | | MMLU-Pro | 72.5 | 72.8 | 58.6 | 82.1 | 58.1 | 93.0 | 94.0 | | HLE | 19.0 | 12.8 | 11.4 | 19.4 | 12.3 | 39.0 | 56.0 | | CRUXEval | 85.8 | 84.6 | 76.7 | 74.7 | 66.4 | 100.0 | 95.0 | | Reasoning | / | / | / | / | / | / | / | | ARC-Challenge | 97.4 | 96.8 | 95.9 | 97.6 | 96.9 | 99.0 | 98.0 | | ARC-Easy | 99.4 | 98.6 | 97.9 | 99.3 | 99.0 | 100.0 | 100.0 | | HellaSwag | 97.9 | 95.9 | 92.1 | 94.3 | 91.4 | 93.0 | 96.0 | | Agentic benchmarks | / | / | / | / | / | / | / | | OSWorld-Verified (automation) | 0.780 | 0.698 | 0.676 | 0.734 | 0.747 | 0.756 | 0.790 | | OSWorld-V2 (automation) | 0.737 | 0.636 | 0.640 | 0.687 | 0.659 | 0.744 | 0.761 | | BFCL (tool calling) | 98.2 | 96.6 | 94.9 | 96.4 | 94.2 | 94.7 | 97.3 | | ToolRet (tool retrieval) | 70.6 | 67.3 | 70.2 | 65.0 | 60.4 | 72.7 | 74.8 | | When2Call | 85.2 | 86.5 | 89.7 | 81.7 | 70.2 | 78.3 | 86.7 | | RAGTruth | 84.8 | 82.5 | 82.7 | 75.1 | 77.0 | 72.5 | 69.8 | | Efficiency | / | / | / | / | / | / | / | | Median API latency | 183 ms | 151 ms | 145 ms | 196 ms | 326 ms | ~2.0 s | ~3.5 s | | Cost (per 1k decisions) | $0.06 | $0.06 | $0.04 | $0.042 | $0.10 | $3.33 | $10.17 | Latency is the median API time per decision, as the caller sees it, network included; ~ marks an approximate figure. Decision Index vision (public). | Benchmark | Drex Max | GPT-6 Luna Decisions | | Overall | / | / | | Public Vision Index | 74.5 | 63.9 | | Perception | / | / | | CV-Bench | 86.3 | 73.8 | | BLINK | 74.1 | 63.7 | | RealWorldQA | 84.0 | 75.0 | | Winoground | 93.0 | 83.8 | | Documents & charts | / | / | | CharXiv | 86.1 | 78.8 | | InfographicVQA | 98.8 | 93.8 | | KIE (CORD + FUNSD) | 95.5 | 97.5 | | Agentic | / | / | | Mind2Web | 88.6 | 81.2 | | Reasoning & safety | / | / | | R-Bench-M | 48.9 | 32.5 | | MMMU-Pro vision | 53.6 | 41.2 | | Hateful Memes (moderation) | 70.6 | 71.2 | Fast and cheap enough for every step. A generative model pays for every token it writes. Drex Max writes nothing, so a decision costs one pass over the input no matter how many options it scores. That makes it cheap enough to call on every step of every task. The recordings in this post show what that adds up to: an agent that books a flight or watches a live camera, with Drex Max making each decision along the way. Pricing and availability. Drex Max is available today through the Nace API at $0.06 per million input tokens, with a 262K-token context window. Sign up at console.nace.ai and get $25 in free credits to try it on your own screens.