List your company

Situational Grounding on GROUND-Eval

53Sorting Fruits (1P)MERGE
-2.1212.1926.540.81Mar 19, 2026

Evaluation results

MethodLinks
MERGEVLM=Gemini 2.5 Flash, Method=Ours2026.035343482022263636350.56
MERGEVLM=GPT-4o, Method=Ours2026.034642484738224450420.36
MERGEVLM=GPT-5, Method=Ours2026.03463648294240500381.39
MERGEVLM=Gemini 2.5 Flash Video, Method=Ours2026.034543551945245022390.56
GPT-5VLM=GPT-5, Method=VLM-only2026.03112932151735380245.52
GPT-4oVLM=GPT-4o, Method=VLM-only2026.0302937227222515230.66
Gemini 2.5 FlashVLM=Gemini 2.5 Flash, Method=VLM-only2026.0301913777134103.23
Gemini 2.5 Flash VideoVLM=Gemini 2.5 Flash Video, Method=VLM-only2026.0302418108152917162.77