Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Agent identification on Liar’s Dice (500 eval agents)

89.5Top-1 Accuracy

Trajectory

76.08479.56783.0586.533Jul 1, 2026
Updated 22d ago

Evaluation Results

MethodLinks
2026.07
89.5
2026.07
83.8
2026.07
79.6
2026.07
76.6