Vals

Composo.ai

This company develops an evaluation platform for large language model applications to help developers and subject matter experts monitor and benchmark AI performance.

LayerLens

This company develops evaluation and testing infrastructure for artificial intelligence teams to assess model performance and agent readiness within synthetic production environments.

Coval

This company provides a testing and evaluation platform for businesses to simulate, monitor, and quality-assure voice artificial intelligence agents across their development lifecycle.

Voice Arena

Voice Arena develops benchmarking infrastructure and human-evaluated datasets to measure the performance and naturalness of voice artificial intelligence models for businesses.

Patronus AI

This company develops an automated evaluation platform and training simulations to detect errors and safety risks in large language models for enterprise developers.

Composo

This company develops an evaluation platform for enterprises to test, monitor and optimise the accuracy of large language model applications.

AI Ops

This company develops an automated testing and diagnostic platform for artificial intelligence models to serve enterprise developers in the automotive, healthcare and retail sectors.

Robocurve

This company develops open-source tools and independent benchmarks to evaluate the capabilities of artificial intelligence models and robotics for researchers and developers.