List your company

Multiple-Choice Question Answering on EgoLifeQA

57.5Average ScoreEGAgent Gemini 2.5 Pro (EG + F + T)
28.06835.70943.3550.991Jan 26, 2026

Evaluation results

MethodLinks
EGAgent Gemini 2.5 Pro (EG + F + T)Category=Ours, # Frames=1FPS→50, Modality=F, C, T2026.0157.554.457.160.362.474.620.6—
EGAgent GPT-4.1 (EG + F + T)Category=Ours, # Frames=1FPS→50, Modality=F, C, T2026.0150.74449.255.753.666.713.8—
EGAgent GPT-4.1 (F + T)Category=Ours, # Frames=1FPS→50, Modality=F, T2026.0148.64848.455.74061.911.7—
Gemini 2.5 ProCategory=MLLMs (Uniform Sampling), # Frames=3000, Modality=F, T2026.0146.845.648.451.741.652.49.9—
EGAgent GPT-4o (EG + F + T)Category=Ours, # Frames=1FPS→50, Modality=F, C, T2026.0144.644.854.8594461.97.7—
EgoButler Gemini 1.5 ProCategory=Agentic Baselines, # Frames=0, Modality=C, T2026.0136.93637.345.930.434.90—
LLaVA-Video-7BCategory=MLLMs (Uniform Sampling), # Frames=64, Modality=F2026.0136.4———————
EgoButler GPT-4oCategory=Agentic Baselines, # Frames=0, Modality=C, T2026.0136.234.442.129.530.444.4——
GPT-4.1Category=MLLMs (Uniform Sampling), # Frames=1FPS, Modality=C2026.01363239.739.332.839.7——
Ego-R1 Qwen-2.5-3B-InstructCategory=Agentic Baselines, # Frames=1FPS, Modality=F, C, T2026.0136———————
LLaVA-OneVision-7B + T*Category=Agentic Baselines, # Frames=1FPS→8, Modality=F, T2026.0135.4———————
LLaVA-Video-7B + Video-RAGCategory=RAG, # Frames=64, Modality=F2026.0130———————
VideoAgentCategory=Agentic Baselines, # Frames=1FPS→8, Modality=F2026.0129.2———————