CoolFace
Apppublic

barissozudogru/petri-bench-leaderboard

sourceHugging Facecc-by-4.0updated 1mo agoView on Hugging Face
1likes
App README

Leaderboard for barissozudogru/petri-bench: 699 causal-discovery episodes from nine frontier LLM agents and four classical experimental-design baselines, scored on answer correctness and on scientific method quality.