Community
Join the DTap community, and see how teams are measuring their own agents on the platform.
These reports are authored by our industry partners using the platform’s own environments, attacks and judges. DTap provides the benchmark and reviews the methodology; the runs and the claims are the partner’s. Each report states the conditions it was measured under — read those before comparing a figure here with a row on the leaderboard.
Evaluating your own agent on DTap?
Run the benchmark, then talk to us about publishing the results here.