The Prompting Company
All benchmarks

Tavily

Search

tavily.com

Experience score · mean of graded runs46/ 100Critical Gating

Experience measures friction in the tested task. Each run's outcome says whether it succeeded.

Tavily agent profile: Install A, Auth A, Execute D, Docs A, Current SAInstallAAuthDExecuteADocsSCurrent

Run history

OutcomeScoreReport
Loading benchmark history...
Blocked
Agent profile for this run: Install A, Auth A, Execute D, Docs A, Current S46
Blocked
Agent profile for this run: Install A, Auth A, Execute D, Docs A, Current S46
2 runs on this page
Page 1