List your company

Multimodal Video Evaluation on Video-MME Sub (test)

87.8AccuracyGemini 2.5 Pro
58.26465.93273.681.268Mar 30, 2026

Evaluation results

MethodLinks
Gemini 2.5 ProCategory=API call only2026.0387.8
Gemini 3 ProCategory=API call only2026.0387.5
GPT-5Category=API call only2026.0386.9
Gemini 2.5 FlashCategory=API call only2026.0384.2
GPT-5 miniCategory=API call only2026.0382.3
Claude Sonnet 4.5Category=API call only2026.0380.5
MolmoPoint-8BCategory=MolmoPoint2026.0376.9
Keye-VL-1.5-8BCategory=Open weights2026.0376.2
Molmo2-8BCategory=Fully open2026.0375.8
Eagle2.5-8BCategory=Open weights2026.0375.7
Molmo2-4BCategory=Fully open2026.0375.7
GLM-4.1V-9BCategory=Open weights2026.0375.6
Qwen3-VL-8BCategory=Open weights2026.0375.2
Qwen3-VL-4BCategory=Open weights2026.0374
MiniCPM-V-4.5-8BCategory=Open weights2026.0373.5
LLaVA-Video-7BCategory=Fully open2026.0369.7
VideoChat-Flash-7BCategory=Fully open2026.0369.7
Molmo2-O-7BCategory=Fully open2026.0369.2
InternVL3.5-4BCategory=Open weights2026.0368.6
InternVL3.5-8BCategory=Open weights2026.0368.6
PLM-8BCategory=Fully open2026.0365.4
PLM-3BCategory=Fully open2026.0359.4