We are thrilled to announce a partnership with the Publications division of the American Chemical Society (ACS) and ACS Ventures, a world leader in scientific publishing. 

SummaryThis evaluation compares the performance of Consensus and Google Scholar on the core task of a literature review: finding relevant papers. Using 500 real user queries and ~10,000 query–paper pairs, we evaluated top-10 results from each system with LLM-based relevance scoring (0–4 scale), blinded to source. Consensus outperformed Google Scholar across all key search relevance metrics: achieving 4.6% higher average precision and stronger DCG scores, meaning it not only finds more relevant papers but also ranks them with more precision. The advantage across metrics is most pronounced in the top five results, where researchers spend most of their time. For researchers, students, and professionals, this means less time sifting and more time learning, proof that smarter academic search is not only possible, and it’s already here.1. Introduction: Why This Evaluation?Google Scholar is the gold standard in academic search. While new AI tools (including Consensus) have gained traction in recent years, Google Scholar still dwarfs the rest of us in traffic and usage. Despite its clunky interface, Scholar is still widely considered the most reliable way to find relevant research, quickly.

Agents Need Powerful Tools Just Like HumansDiscovery is made at the edge of what is known. In order to drive breakthroughs, we must reduce the time it takes people to get to that edge, so they can more easily push past it. This is our goal with Consensus. This means building tools for end users who are doing important research. But, in a world with agents helping push progress, it also means equipping agents with the best tools possible to execute tasks. Biomni is building an AI scientist for biomedical research that supports the entire scientific process—from literature search to experimental design. Their agent now relies on the Consensus scientific search API to power literature discovery. At any stage of research where literature search is needed, Consensus is the engine behind it.In head-to-head testing against other search approaches, Consensus ranked highest for result relevance and quality. The Consensus API searches across a curated corpus of 200M+ academic papers, conference proceedings, and preprints, using a proprietary search stack designed for precision. 

A Step Toward Accessible Expert Knowledge for AllScientific research is the most valuable source of knowledge that humans have ever created. Yet, there is no easy way to search and consume it. Combing through the literature is a laborious part of a researcher's process and unambiguously out-of-reach for any non-academic.We are building Consensus to change this.Consensus is an AI search engine designed to make searching for and consuming scientific research papers easier. We strive to enable scientists to stop searching and get back to doing real science, and to empower a new generation of citizen scientists by equipping them with access to real evidence.

Today, we are thrilled to unveil the most monumental upgrade to Consensus ever!We have dubbed it Consensus 2.0. Consensus 2.0 reflects the commitment to our users to build the BEST academic search engine in the world. We have completely overhauled the way a Consensus search works, improving its speed, precision, and most importantly, our core search relevance.What Has Changed?

At Consensus, our mission is to make the world's expert knowledge consumable by all. We publicly launched our search engine in September 2022 which uses AI to surface and synthesize answers from scientific research. Since then, we have experienced rapid growth, attracting nearly 200,000 registered users driven exclusively by word-of-mouth sharing.Today, we are thrilled to announce that we have recently raised a $3M Seed funding round led by Draper Associates (Tesla, Coinbase, Robinhood, Twitch, SpaceX, and more than 20 more eventual unicorns) with participation from investors Kevin Carter (Snap, Slack, Pinterest), Brian Pokorny (Twitter, Square, Stitcher), Nomad Capital (Open Sea, Intercom, Deel) and Alumni Ventures (Compass, Deliverr). Additional investors in the round include reinvestment from pre-seed round backer Winklevoss Capital, and new investors Des Traynor (founder, Intercom), Rob May (AI Operator Fund), Billy Draper (PathVC), Kindergarten Ventures, and David Dohan (OpenAI Research).Our vision is to be the go-to source in anyone's search for expert information - with scientific literature being a natural starting point. Searching for vetted, unbiased information has long been an arduous and painful process. It is our belief that, if used thoughtfully, carefully, and elegantly, artificial intelligence can change this equation. This round of financing further empowers our amazing team to keep building toward the goal of making the search for expert information delightful and user-friendly.Read more about our funding announcement at VentureBeat: Consensus raises $3M to revolutionize scientific web search