Skip to content
Advertisement

Vals AI

Independent Evaluation, Unbiased Benchmarks

Evaluation & Benchmarking
Visit website

Vals AI develops and runs independent, domain-specific benchmarks for foundation models, publishing results through the Vals Index across more than 25 benchmarks spanning finance, law, software engineering, and healthcare, including third-party suites such as SWE-bench and Terminal-Bench alongside its own tasks.

Text
Advertisement