26companies
$1.4Bpublished funding, 14 companies
2024median founding year
1with a partner program

Offerings: Evals and benchmarks (24), RL environments (22), Training data (15), Human data (12), Data annotation (6), Simulation (2), RL infrastructure (1).

Companies (26), by published funding

Figures as published by each company or the source on its profile. n/a means no source found.

CompanyWhat it doesBased inFundingPartner program
AliceThe former ActiveFence. Sells safety and security datasets, RL environments and red teaming to model labs, plus guardrail and moderation software.Israel$280Mn/a
BugcrowdCrowdsourced security testing company that also offers AI developers cyber training environments and an exploitation benchmark.United States$230Mn/a
TuringTraining data, evals and RL environments for coding, knowledge work and STEM, plus enterprise agent deployment.United States$225MYes
LabelboxLabeling platform company that now sells RL environments, expert preference data and evals to frontier labs.United States$189MNo
ClaruSupplies custom and licensed video, robot demonstrations and annotation for robotics and world model work.United States$170Mn/a
LatchLatchBio sells biotech cloud software and bioinformatics workflows, and builds evals for biology AI agents.United States$163Mn/a
Gray Swan AIAI security firm offering pre-release adversarial testing plus runtime filtering and monitoring.United States$50Mn/a
DatacurveExpert coding data vendor offering RL environments, benchmarks and evals to model labs and developer tool companies.United States$17.7Mn/a
Chakra LabsWrites expert task sets and graders, including computer-use environments, for model training and testing in finance, law and other fields.United States$10.1Mn/a
CollinearSells simulated environments, agent evals and synthetic training data to labs and enterprise teams building agents.United States$10MNo
IdlerSells RL environments, benchmarks and eval sets built from real production work.United States$9.5Mn/a
IncalmoBuilds RL cyber ranges and security evals for training and testing cybersecurity-capable models.United States$8.7Mn/a
QuesmaPublishes coding agent benchmarks, builds RL environments, and sells agent cost and workflow analytics.Poland$2.3Mn/a
AbundantBuilds reinforcement learning environments, benchmarks and datasets for labs and companies working on AI agents.United States$500Kn/a
AI AstrolabeData and evaluation vendor centered on Arabic dialects and other underserved languages, covering text, speech, images and safety data.United Statesn/an/a
AITraining.jobsExpert data shop run by O-mega Enterprise that staffs US professionals on evals, rubrics, preference data and RL tasks for AI developers.Delaware)n/an/a
AppenHuman data vendor. Labs and product teams buy its labeling, expert review, model evaluation and RL environment work.AustraliaPublicNo
ARIMLABSCreates simulated workspaces and verifiable benchmarks for agents doing security, incident response and software tasks.Polandn/an/a
exponentialSells multi-agent security environments, security training data and adaptive red team testing.Germanyn/an/a
G2iRuns managed coding data projects and places contract engineers inside lab teams for post-training work.United StatesSelf-fundedn/a
InnodataData engineering firm supplying training data, human feedback, RL environments, evals and red teaming.United Statesn/an/a
NoumadBuilds formally verified RL environments on open problems in machine learning, science, robotics and security.United Statesn/an/a
Olam LabsBuilds multi-agent simulations, behavioral evals and game-based data for studying social and safety behavior.United Statesn/an/a
RL LabsMakes multi-step coding environments that run for a long time, used by frontier labs to train models on complex engineering work.n/an/an/a
TELUS DigitalTELUS unit supplying expert data, labeling, RL environments, red teaming, evals and physical AI datasets.CanadaPublicn/a
Trajectory LabsSafety evals, expert red teaming and RL environments for finding and fixing model vulnerabilities.United Statesn/an/a