Best AI Evaluation Companies

Vendor profileChecked Nov 8, 2026

Vals AI

Vals AI · vals.ai · Last checked:

  • Independent evaluator
  • Benchmarks and custom evaluations

Company status

Active.

Sources 1, 2, 3, 4 · checked 2026-11-08

Capabilities

  • Independent public benchmarks across legal, finance, tax, healthcare, coding, and other domains; states it runs all its own evaluations
  • Many benchmarks use private or proprietary test sets (e.g., Tax Agent Bench, CorpFin v2)
  • Builds evaluations with domain experts and reference institutions; invites project discussions and benchmark collaborations
  • Public-sector work: policy briefings on what an evaluation measures, research collaborations

Sources 1, 2, 3, 4 · checked 2026-11-08

Who it tends to fit

  • Organizations wanting a domain benchmark built with an independent evaluator
  • Public-sector teams needing evaluation briefings

Sources 1, 2, 3, 4 · checked 2026-11-08

Pricing

Contact vendor (discuss a project)

Sources 1, 2, 3, 4 · checked 2026-11-08

Published certifications

None found / not verified. This is not a finding that Vals AI lacks certifications; ask the vendor for documentation.

No security certification found on the official site on 2026-11-08; site links a vulnerability disclosure page only.

Listed as stated by the vendor. Scope can differ by product or subsidiary; request current reports.

Sources 1, 2, 3, 4 · checked 2026-11-08

Limitations to check

  • No public pricing or published engagement terms for custom work
  • No security certifications published

Sources 1, 2, 3, 4 · checked 2026-11-08

Sources

  1. Homepage: 'Independent Evaluation, Unbiased Benchmarks'; 'We run all of our own evaluations and create many of our benchmarks in-house'www.vals.ai/homeChecked 2026-11-08
  2. About page: 'The independent evaluator of artificial intelligence'; privately held test sets; builds benchmarks with reference institutions; invites help shaping a benchmarkwww.vals.ai/aboutChecked 2026-11-08
  3. Government page: build rigorous evaluations with domain experts; discuss a project; request a policy briefingwww.vals.ai/govChecked 2026-11-08
  4. Benchmarks page: legal, finance, tax, healthcare, coding domains; several private or proprietary benchmarkswww.vals.ai/benchmarksChecked 2026-11-08

Report a correction: [email protected]. Facts are re-checked at least every 90 days.