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

Task Planning on EgoPlan-Benchmark1 (val)

47.4Accuracy

PhysBrain-8B

23.37629.61335.8542.087Dec 18, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.12
47.4
2025.12
45.9
2025.12
44.3
2025.12
43.9
2025.12
42.2
2025.12
40.8
2025.12
39.5
2025.12
38.6
2025.12
28.1
2025.12
27.8
2025.12
24.3