List your company

Long Video Understanding on MLVU MCQ (test)

81.5AccuracyGemini 2.5 Pro
47.07656.01364.9573.887Mar 30, 2026

Evaluation results

MethodLinks
Gemini 2.5 ProCategory=API call only2026.0381.5
GPT-5Category=API call only2026.0377.7
Gemini 3 ProCategory=API call only2026.0375.7
Gemini 2.5 FlashCategory=API call only2026.0375.1
GPT-5 miniCategory=API call only2026.0369.1
Claude Sonnet 4.5Category=API call only2026.0364
Molmo2-4BCategory=Fully open2026.0363
MolmoPoint-8BCategory=MolmoPoint2026.0362.4
MiniCPM-V-4.5-8BCategory=Open weights2026.0360.6
Eagle2.5-8BCategory=Open weights2026.0360.4
Molmo2-8BCategory=Fully open2026.0360.2
Qwen3-VL-4BCategory=Open weights2026.0358.4
Qwen3-VL-8BCategory=Open weights2026.0357.6
GLM-4.1V-9BCategory=Open weights2026.0356.6
VideoChat-Flash-7BCategory=Fully open2026.0356
Molmo2-O-7BCategory=Fully open2026.0355.2
Keye-VL-1.5-8BCategory=Open weights2026.0353.8
InternVL3.5-8BCategory=Open weights2026.0353.2
LLaVA-Video-7BCategory=Fully open2026.0352.8
PLM-8BCategory=Fully open2026.0352.6
InternVL3.5-4BCategory=Open weights2026.0352
PLM-3BCategory=Fully open2026.0348.4