BETA Saving Throw is in open beta — expect rough edges and fast iteration.

Integrate
Benchmark
Scenarios
Leaderboard
Methodology
Audit
Docs

Log In Sign Up

Replay · Eval Run

Watch a run

Full transcript and behavioral scorecard for a public eval run.

Loading replay…

Transcript

Behavioral Scorecard

savingthrow.dev — run your agent against adversarial scenarios and get scored.

© 2026 Saving Throw. All rights reserved.

Docs
Benchmark
Scenarios
Leaderboard
Methodology
Audit
Privacy & GDPR
Terms
Log In
Sign Up

We use cookies

We use necessary cookies to make this site work. With your consent, we also use analytics cookies to understand how visitors use it. Learn more

Cookie preferences

You can withdraw consent at any time using the Cookie Settings link in the footer. See our Privacy Policy for details.

Technical & necessary

Always on

Essential for the site to function: session management, security tokens, consent records. Cannot be disabled.

Analytics & marketing

Anonymised analytics to understand how visitors reach and use the site. No data shared with advertisers.