List your company
ResearchFormerly WizWand

Multiple Choice Video Question Answering on EgoSchema

72.2AccuracyGemini-1.5-Pro
34.34444.1725463.828Jun 18, 2024Sep 25, 2024Jan 2, 2025Apr 11, 2025Jul 19, 2025Oct 26, 2025Feb 3, 2026
Updated 8mo ago

Evaluation results

MethodLinks
Gemini-1.5-Prozero-shot=true2025.0372.2
VideoTreeLLM Size=GPT-4, Vision Encoder=Unknown, Training Strategy=Training-free2024.1166.2
VideoTreeLLM Size=GPT-4, Vision Encoder=Unknown, Training Strategy=Training-free2024.1166.2
VideoTreeLLM Size=GPT-4, Vision Encoder=Unknown, Training Strategy=Training-free2024.1166.2
Gemini-1.5-Flashzero-shot=true2025.0365.7
DrVideoLLM=GPT-42024.0661
VideoAgentLLM Size=GPT-4, Vision Encoder=Unknown, Training Strategy=Training-free2024.1160.2
VideoAgentLLM Size=GPT-4, Vision Encoder=Unknown, Training Strategy=Training-free2024.1160.2
VideoAgentLLM Size=GPT-4, Vision Encoder=Unknown, Training Strategy=Training-free2024.1160.2
VideoAgentLLM=GPT-4, Reference=[14]2024.0660.2
LLaVA-OV-7Bzero-shot=true2025.0360.1
LLaVAction-7Bzero-shot=true2025.0359
TS-LLaVALLM Size=34B, Vision Encoder=CLIP-L, Training Strategy=Training-free2024.1157.8
TS-LLaVALLM Size=34B, Vision Encoder=CLIP-L, Training Strategy=Training-free2024.1157.8
TS-LLaVALLM Size=34B, Vision Encoder=CLIP-L, Training Strategy=Training-free2024.1157.8
LLaVA-Video-7Bzero-shot=true2025.0357.3
KTV-34B-denseLLM Size=34B, Vis Encoder=CLIP-L, Training Regime=Training-Free, Variant=dense2026.0257
DYTOLLM Size=34B, Vis Encoder=CLIP-L, Training Regime=Training-Free2026.0256.8
MovieChat+LLM Size=7B, Vision Encoder=CLIP-G, Training Strategy=Video-trained2024.1156.4
MovieChat+LLM Size=7B, Vision Encoder=CLIP-G, Training Strategy=Video-trained2024.1156.4
SF-LLAVALLM Size=34B, Vision Encoder=CLIP-L, Training Strategy=Training-free2024.1155.8
SF-LLAVALLM Size=34B, Vision Encoder=CLIP-L, Training Strategy=Training-free2024.1155.8
SF-LLAVALLM Size=34B, Vision Encoder=CLIP-L, Training Strategy=Training-free2024.1155.8
KTV-34B-sparseLLM Size=34B, Vis Encoder=CLIP-L, Training Regime=Training-Free, Variant=sparse2026.0255.6
KTV-34B-normalLLM Size=34B, Vis Encoder=CLIP-L, Training Regime=Training-Free, Variant=normal2026.0255.6
SF-LLaVA-7BLLM Size=34B, Vis Encoder=CLIP-L, Training Regime=Training-Free2026.0255
VideoAgentLLM=GPT-4, Reference=[61]2024.0654.1
IG-VLMLLM Size=34B, Vision Encoder=CLIP-L, Training Strategy=Training-free2024.1153.6
IG-VLMLLM Size=34B, Vision Encoder=CLIP-L, Training Strategy=Training-free2024.1153.6
IG-VLMLLM Size=34B, Vision Encoder=CLIP-L, Training Strategy=Training-free2024.1153.6
IG-VLMLLM Size=34B, Vis Encoder=CLIP-L, Training Regime=Training-Free2026.0253.4
Video-LLAMA2LLM Size=46.7B, Vision Encoder=CLIP-L, Training Strategy=Video-trained2024.1153.3
VideoLLaMA2LLM Size=46.7B, Vis Encoder=CLIP-L, Training Regime=Training-Based2026.0253.3
Video-LLaMA2LLM Size=7B, Vision Encoder=CLIP-L, Training Strategy=Video-trained2024.1151.7
Video-LLaMA2LLM Size=7B, Vision Encoder=CLIP-L, Training Strategy=Video-trained2024.1151.7
MoReVQALLM=PaLM-22024.0651.7
VideoLLaMA2-7Bzero-shot=true2025.0351.7
KTV-7B-denseLLM Size=7B, Vis Encoder=CLIP-L, Training Regime=Training-Free, Variant=dense2026.0251
KTV-7B-normalLLM Size=7B, Vis Encoder=CLIP-L, Training Regime=Training-Free, Variant=normal2026.0250.4
LLoViLLM Size=GPT-3.5, Vision Encoder=Unknown, Training Strategy=Training-free2024.1150.3
LLoViLLM Size=GPT-3.5, Vision Encoder=Unknown, Training Strategy=Training-free2024.1150.3
LLoViLLM Size=GPT-3.5, Vision Encoder=Unknown, Training Strategy=Training-free2024.1150.3
LLoViLLM=GPT-3.52024.0650.3
TS-LLaVALLM Size=7B, Vision Encoder=CLIP-L, Training Strategy=Training-free2024.1150.2
TS-LLaVALLM Size=7B, Vision Encoder=CLIP-L, Training Strategy=Training-free2024.1150.2
KTV-7B-sparseLLM Size=7B, Vis Encoder=CLIP-L, Training Regime=Training-Free, Variant=sparse2026.0249.6
DYTOLLM Size=7B, Vis Encoder=CLIP-L, Training Regime=Training-Free2026.0248.6
VamosLLM=GPT-42024.0648.3
SF-LLaVALLM Size=7B, Vision Encoder=CLIP-L, Training Strategy=Training-free2024.1147.2
SF-LLaVALLM Size=7B, Vision Encoder=CLIP-L, Training Strategy=Training-free2024.1147.2
SF-LLaVA-7BLLM Size=7B, Vis Encoder=CLIP-L, Training Regime=Training-Free2026.0244.2
DeepStack-LLLM Size=7B, Vision Encoder=CLIP-L, Training Strategy=Video-trained2024.1138.4
DeepStack-LLLM Size=7B, Vision Encoder=CLIP-L, Training Strategy=Video-trained2024.1138.4
MVULLM=Mistral-13B2024.0637.6
Video-LLaVALLM Size=7B, Vision Encoder=ViT-L, Training Strategy=Video-trained2024.1137
Video-LLaVALLM Size=7B, Vision Encoder=ViT-L, Training Strategy=Video-trained2024.1137
M3LLM Size=7B, Vision Encoder=CLIP-L, Training Strategy=Video-trained2024.1136.8
M3LLM Size=7B, Vision Encoder=CLIP-L, Training Strategy=Video-trained2024.1136.8
IG-VLMLLM Size=7B, Vision Encoder=CLIP-L, Training Strategy=Training-free2024.1135.8
IG-VLMLLM Size=7B, Vision Encoder=CLIP-L, Training Strategy=Training-free2024.1135.8
IG-VLMLLM Size=7B, Vis Encoder=CLIP-L, Training Regime=Training-Free2026.0235.8