List your company

General Video Understanding on NExT-QA

86.3AccuracyGPT-4o
75.3878.21581.0583.885Jun 1, 2026

Evaluation results

MethodLinks
GPT-4o2026.0686.3
Molmo2-8B2026.0686.2
VideoChat-Flash-7B2026.0685.5
Gemini 1.5 ProSource=[60]2026.0685.3
Eagle-X5-7B2026.0685
Gemini 1.5 ProSource=[59]2026.0684.3
Molmo2-O-7B2026.0684.3
ReMoRa-7B2026.0684.2
AdaCodecToken budget=comparable, Backbone=Qwen2-VL-7B2026.0684.2
PLM-7B2026.0684.1
Qwen2-VL-7B2026.0683.4
GPT-4o mini2026.0683.2
LLaVA-Video-7B2026.0683.2
AdaCodecToken budget=1/7, Backbone=Qwen2-VL-7B2026.0683.1
CoPE-VideoLM-7B2026.0682.1
Gemini 1.5 Flash2026.0681.8
InternVL2-8B2026.0681.7
GLM-4V-9B2026.0681.3
Claude 3.5 Sonnet2026.0679.2
MiniCPM-V-2.6-8B2026.0678.8
Key-VL-1.5-8B2026.0675.8