# AI Evaluation Companies

> An independent US reference on companies that sell AI model evaluation, red-teaming and evaluation software, with each vendor's published prices, plan limits and security claims, read from its own pages on 7 November 2026. Facts that a vendor does not publish are marked "Not published". The site introduces teams to vendors and may be paid a fee by the vendor; it does not run evaluations, test vendors or handle anyone's data.

## Reference pages
- [AI Evaluation Companies](https://aievaluationcompanies.com/): the four types of evaluation, services vs tooling, a shortlist with published prices, pricing models and contract checks
- [Vendors and tools](https://aievaluationcompanies.com/vendors-and-tools/): every vendor with delivery model, published pricing, security claims, ownership changes and a dated terms changelog
- [Types of AI evaluation](https://aievaluationcompanies.com/types-of-ai-evaluation/): capability, safety and red-team, human preference and regression testing, and which decision each one answers
- [Red-teaming services](https://aievaluationcompanies.com/red-teaming-services/): companies selling adversarial testing, how to scope an engagement and what the report should contain
- [Eval budget](https://aievaluationcompanies.com/eval-budget/): arithmetic for a human rating round and tooling plans from published prices (a planning figure, not a quote)

## Blog
- [How to build an eval set from your own logs](https://aievaluationcompanies.com/readouts/how-to-build-an-eval-set-from-your-own-logs/): How to build an eval set from your own production logs: what to strip out first, how to sample, writing references and rubrics, and keeping the set fresh.
- [Human preference evals or automated graders?](https://aievaluationcompanies.com/readouts/human-preference-evals-or-automated-graders/): Human preference evals or automated graders: what each measures, what each costs from published prices, where model graders go wrong, how to calibrate.
- [Red-teaming vs benchmarking: what are you buying?](https://aievaluationcompanies.com/readouts/red-teaming-vs-benchmarking/): Red-teaming vs benchmarking for AI systems: what each one measures, what the deliverable looks like, when to buy which, and how they feed each other.

## About
- [How this works](https://aievaluationcompanies.com/how-we-connect-teams/): what happens after a brief is sent and how introductions are paid for
- [Privacy notice](https://aievaluationcompanies.com/privacy/)