doteval
doteval is an AI-assisted evaluation workspace that simplifies the creation of high-signal evaluations, alignment of LLM judges, and definition of rewards for reinforcement learning, all within a single platform. It offers a Cursor-like experience to edit evaluations-as-code against a YAML schema, enabling users to version evaluations across checkpoints, replace manual effort with AI-generated diffs, and compare evaluation runs on tight execution loops to align them with proprietary data. doteval supports the specification of fine-grained rubrics and aligned graders, facilitating rapid iteration and high-quality evaluation datasets. Users can confidently determine model upgrades or prompt improvements and export specifications for reinforcement learning training. It is designed to accelerate the evaluation and reward creation process by 10 to 100 times, making it a valuable tool for frontier AI teams benchmarking complex model tasks.
Learn more
LayerLens
LayerLens is an independent AI model evaluation platform for understanding how models perform through verified results across benchmarks, prompt-level results, agentic benchmarks, and audit-ready comparisons across vendors. It helps teams compare more than 200 AI models side by side, with transparent benchmarks, model comparison tools, and consistent evaluation methods for accuracy, latency, behavior, and real-world applicability. LayerLens is built for deep model analysis through Spaces, where teams can group benchmarks and evaluations, explore task strengths, and track performance patterns in context. It supports continuous evaluation by running ongoing evals across model versions, prompt changes, judge updates, and live traces, helping teams detect quality regressions, drift, silent failures, contamination, and policy issues before they affect production.
Learn more
HoneyHive
AI engineering doesn't have to be a black box. Get full visibility with tools for tracing, evaluation, prompt management, and more. HoneyHive is an AI observability and evaluation platform designed to assist teams in building reliable generative AI applications. It offers tools for evaluating, testing, and monitoring AI models, enabling engineers, product managers, and domain experts to collaborate effectively. Measure quality over large test suites to identify improvements and regressions with each iteration. Track usage, feedback, and quality at scale, facilitating the identification of issues and driving continuous improvements. HoneyHive supports integration with various model providers and frameworks, offering flexibility and scalability to meet diverse organizational needs. It is suitable for teams aiming to ensure the quality and performance of their AI agents, providing a unified platform for evaluation, monitoring, and prompt management.
Learn more
Latitude
Latitude is an open-source prompt engineering platform designed to help product teams build, evaluate, and deploy AI models efficiently. It allows users to import and manage prompts at scale, refine them with real or synthetic data, and track the performance of AI models using LLM-as-judge or human-in-the-loop evaluations. With powerful tools for dataset management and automatic logging, Latitude simplifies the process of fine-tuning models and improving AI performance, making it an essential platform for businesses focused on deploying high-quality AI applications.
Learn more
