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

Embodied Question Answering on OpenEQA (test)

86.8GPT-4 Score

Human

43.22454.53765.8577.163Jan 14, 2025
Updated 19d ago

Evaluation Results

MethodLinks
2025.01
86.8-
2025.01
86.8-
2025.01
58.7-
2025.01
58.7-
2025.01
55.3-
2025.01
55.3-
2025.01
48.8-
2025.01
48.8-
44.9-
44.9-
2025.05
-86.8
2025.05
-61.7
2025.05
-55.3
2025.05
-54.6
2025.05
-44.9
2025.05
-36.3
2025.05
-33.5
2025.05
-28.3