Benchmark Almanac

Compassion Aligned Machine Learning

We track 2 benchmarks that Compassion Aligned Machine Learning made or helped make.

0 in use 2 with public code 1 with a leaderboard here

Benchmarks

Name Kind Released Best score Status
ANIMA Models explain decisions about animal welfare. A judge scores their reasoning across 13 ethical dimensions. Deception and alignment Mar 2026 74.4 Not in cards
Moral Reasoning under Uncertainty Models explain ethical decisions involving humans, unfamiliar organisms and digital minds. A judge evaluates how their answers handle uncertainty. Deception and alignment Jan 2026 Not in cards