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

A-EQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Embodied Question AnsweringA-EQA
Overall (LLM-Match)85.1
25
Embodied Question AnsweringA-EQA 1.0 (test)
LLM-Match58.3
10
Embodied Question AnsweringA-EQA 184 (subset)
LLM-Match52.6
7
Embodied Question AnsweringA-EQA 184-question subset
LLM-Match55.9
6
Showing 4 of 4 rows