Arena.ai
Arena is a community-powered platform designed to evaluate AI models based on real-world usage and feedback. Created by researchers from UC Berkeley, it enables users to test and compare frontier AI models across various tasks. The platform gathers insights from millions of builders, researchers, and creative professionals to generate transparent performance rankings. Arena’s public leaderboard reflects how models perform in practical scenarios rather than controlled benchmarks. Users can compare models side by side and provide feedback that helps shape future AI development. It supports a wide range of use cases, including text generation, coding, image creation, and video production. By leveraging collective input, Arena advances the understanding and improvement of AI technologies.
Learn more
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
Braintrust
Braintrust is an AI observability and evaluation platform designed to help teams build, monitor, and improve AI systems in production. It enables users to capture and inspect real-time traces of AI interactions, including prompts, responses, and tool usage. The platform allows teams to measure performance using automated and human evaluations to ensure output quality. Braintrust helps identify issues such as hallucinations, regressions, and performance drops before they impact users. It supports prompt and model comparisons, making it easier to optimize AI workflows over time. With scalable trace ingestion and real-time monitoring, teams gain full visibility into how their AI systems behave. The platform integrates with multiple programming languages and tools, allowing developers to work within their existing tech stack. Overall, Braintrust provides a comprehensive solution for maintaining and improving AI quality at scale.
Learn more
LLM Scout
LLM Scout is an evaluation and analysis platform designed to help users benchmark, compare, and interpret the performance of large language models across diverse tasks, datasets, and real-world prompts within a unified environment. It enables side-by-side comparisons of models by measuring accuracy, reasoning, factuality, bias, safety, and other key metrics using customizable evaluation suites, curated benchmarks, and domain-specific tests. It supports the ingestion of user-provided data and queries so teams can assess how different models respond to their own real-world workflows or industry-specific needs, and visualize outputs in an intuitive dashboard that highlights performance trends, strengths, and weaknesses. LLM Scout also includes tools for analyzing token usage, latency, cost implications, and model behavior under varied conditions, helping stakeholders make informed decisions about which models best fit specific applications or quality requirements.
Learn more
