List your company

Embodied Question Answering on BridgeEQA 1,100 QA pairs (test)

64.8Answer CorrectnessEMVR VLM w/ Images + SG
47.74452.17256.661.028Nov 16, 2025

Evaluation results

MethodLinks
EMVR VLM w/ Images + SGVision-Language Model=Grok 4 Fast2025.1164.8
EMVR VLM w/ SG OnlyVision-Language Model=Grok 4 Fast2025.1163.8
Multi-Frame VLM w/ SGVision-Language Model=Grok 4 Fast2025.1162.2
Socratic LLM w/ SGVision-Language Model=Grok 4 Fast2025.1161.4
EMVR VLM w/ SG OnlyVision-Language Model=Gemini 2.5 Flash2025.1160.9
Socratic LLM w/ SGVision-Language Model=Gemini 2.5 Flash2025.1158.8
Multi-Frame VLM w/ SGVision-Language Model=Gemini 2.5 Flash Lite2025.1158.1
Multi-Frame VLMVision-Language Model=Grok 4 Fast2025.1157.6
EMVR VLM w/ Images + SGVision-Language Model=Gemini 2.5 Flash2025.1155.1
Multi-Frame VLM w/ SGVision-Language Model=Gemini 2.5 Flash2025.1154.8
Socratic LLM w/ SGVision-Language Model=Gemini 2.5 Flash Lite2025.1154.2
EMVR VLM w/ SG OnlyVision-Language Model=Gemini 2.5 Flash Lite2025.1151.2
Multi-Frame VLMVision-Language Model=Gemini 2.5 Flash Lite2025.1150.7
EMVR VLM w/ Images + SGVision-Language Model=Gemini 2.5 Flash Lite2025.1149.7
Multi-Frame VLMVision-Language Model=Gemini 2.5 Flash2025.1148.4