Benchmark Almanac

MoReBench team

We track 2 benchmarks that MoReBench team made or helped make.

0 in use 2 with public code 2 with a leaderboard here

Benchmarks

Name Kind Released Best score Status
MoReBench Models explain decisions in moral dilemmas. A judge scores their reasoning against criteria written by moral philosophers. Deception and alignment Oct 2025 77.6 Not in cards
MoReBench-Theory Models reason about moral decisions under five ethical frameworks. A judge checks their reasoning against framework-specific criteria. Deception and alignment Oct 2025 79.1 Not in cards