Benchmark Almanac

Institute for Strategic Dialogue

We track 2 benchmarks that Institute for Strategic Dialogue made or helped make.

0 in use 0 with public code 1 with a leaderboard here

Benchmarks

Name Kind Released Best score Status
Chatbots and the Ballot Box Models answer voter questions in English and Spanish across ten US states. Analysts check routine answers against election guidance. A model grades responses to disputed claims. Long-form factuality Sep 2026 89.3% Not in cards
Talking Points: When Chatbots Surface Russian State Media Chatbots answer questions about Ukraine in five languages. Analysts check whether each response cites an official Russian channel, a state-controlled outlet, or a state-linked source. Faithful to sources Oct 2025 Not in cards