List your company

Average Context Length on NExT-GQA for Video Question Answering

55,136.3Average Context Length (tokens)Video-o3
821.88414,922.74229,023.643,124.458May 26, 2026

Evaluation results

MethodLinks
Video-o3Max retrieval / injection=82026.0555,136.3
LongVT-RFTMax retrieval / injection=52026.0516,389
VideoZoomerMax retrieval / injection=42026.0512,254.9
VideoChat-R1.5-7BMax retrieval / injection=22026.058,897.5
LOVE-R1-stage3Max retrieval / injection=22026.058,480.5
DynFrame-8BMax retrieval / injection=12026.056,734.5
Video-R1-7BMax retrieval / injection=02026.053,893.2
Qwen2.5-VL-7BMax retrieval / injection=02026.052,910.9