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

Task Success on ALFWorld (50 eval tasks)

49Success Rate

TraceRetain-CEM-K50

38.641.34446.7Jun 28, 2026
Updated 26d ago

Evaluation Results

MethodLinks
2026.06
499.5229.2
4812.130
2026.06
4811.0826.4
2026.06
4710.8245.2
2026.06
3920.980