List your company

Embodied Question Answering on OpenEQA EM-EQA Episodes up to 32 frames

86.8LLM-Match ScoreHuman
34.48848.06961.6575.231Oct 1, 2025

Evaluation results

MethodLinks
Human2025.1086.8
Gemini 3 FlashQuery Latency [sec]=10.52025.1076.8
Qwen 3.5 Plus2025.1074.1
Gemini 2.5 FlashQuery Latency [sec]=6.82025.1069.8
VL-KnG (GER-L)Query Latency [sec]=0.82025.1055.2
VL-KnG (GER-G)Query Latency [sec]=0.82025.1054.7
VL-KnG (GR)Query Latency [sec]=0.82025.1050.7
GPT-4V2025.1049.6
Gemini 1.0 Pro Vision2025.1044.9
GPT-4 w/ ConceptGraphs2025.1036.5