geekbench

Autonomous mobility service enabling driverless operation on urban roads

AI data platform for annotating text, audio, images, video, and 3D data, plus model evaluation

An open-source hardware platform offering sensors, communication modules, and edge computing devices for prototyping.

A computer vision development platform for managing datasets, training models, and deploying inference services.

Browser extension that automatically captures screen activity and logs to generate defect reports

A developer productivity platform supporting structured code reviews and incremental change management

Responsible AI Institute (RAI Institute) is an independent nonprofit organization dedicated to advancing the adoption of trustworthy AI across industries. It offers actionable AI governance tools, validation and certification programs, and risk monitoring services designed to enable the large-scale implementation of responsible AI. The Institute collaborates with global academic labs, policymakers, and AI providers to ensure alignment with evolving regulations and industry standards. Its product offerings include AI benchmarking, compliance automation, and workforce upskilling programs to support ethical, fair, and transparent AI deployment.

Transluce is a non-profit research organization dedicated to advancing AI technologies by uncovering the internal mechanisms of complex AI models. By automatically generating high-quality, human-interpretable descriptions of neuron components and providing an interactive observability interface, Transluce empowers researchers and users to better understand, query, and guide AI behavior. All tools are scalable and open-source, driving industry standards for AI safety and transparency. Transluce's approach leverages AI agents to analyze large language models, detect hidden behaviors, and support responsible AI deployment through community-validated methods.

Evidently AI is a comprehensive solution designed to help teams build, evaluate, and maintain highly reliable AI products, covering both traditional machine learning models and large language model (LLM) applications. It includes an open-source Python library with 100+ built-in evaluation metrics, as well as a cloud platform that supports AI testing, monitoring, synthetic data generation, and collaborative workflows. Evidently AI enables users to detect data and prediction drift, perform regression and adversarial testing, and manage datasets and evaluations through an intuitive interface, ensuring AI quality throughout the entire product lifecycle.

Ballpark is a fast, intuitive platform that helps product teams gather actionable user feedback throughout the development lifecycle. It enables testing of websites, Figma prototypes, marketing copy, and competitor offerings—no installation required. Ballpark integrates surveys, interactive tasks, and audio-video recording to capture authentic user reactions and in-depth insights. With access to a large global respondent panel and extensive screening options, teams can quickly recruit relevant testers. Unlimited team seats and collaboration features democratize research across organizations, enabling data-driven decisions, shortening project timelines, and improving product-market fit.

Confident AI is a powerful evaluation platform built on the open-source DeepEval framework, designed to help teams systematically test and optimize large language model (LLM) applications. The platform supports a complete evaluation workflow—from dataset creation and custom metrics to continuous monitoring in production—enabling enterprises to compare different LLMs, detect regressions, and improve performance using industry-leading, scenario-based metrics and safeguards. Confident AI fosters collaboration between technical and non-technical team members, seamlessly integrates with CI/CD pipelines, and offers enterprise-grade capabilities including on-premises deployment, SSO, and HIPAA compliance.

Ragas is a powerful and flexible open-source library designed for evaluating LLMs and RAG pipelines. It offers a comprehensive suite of automated evaluation metrics covering dimensions such as factual accuracy, coherence, and relevance, while also supporting synthetic test data generation and online monitoring. Ragas enables benchmarking aligned with industry standards and allows for customizable evaluation workflows to meet diverse needs in research and production environments. Its strong integration capabilities help developers and researchers optimize and ensure the reliability of AI applications.