List your company

Video Understanding on MLVU MCQ (test)

81.5AccuracyGemini 2.5 Pro
47.07656.01364.9573.887Jan 15, 2026

Evaluation results

MethodLinks
Gemini 2.5 ProAccess Type=API call only2026.0181.5
GPT-5Access Type=API call only2026.0177.7
Gemini 3 ProAccess Type=API call only2026.0175.7
Gemini 2.5 FlashAccess Type=API call only2026.0175.1
GPT-5 miniAccess Type=API call only2026.0169.1
Claude Sonnet 4.5Access Type=API call only2026.0164
Molmo2-4BAccess Type=Molmo2 family2026.0163
MiniCPM-V-4.5-8BAccess Type=Open weights only2026.0160.6
Eagle2.5-8BAccess Type=Open weights only2026.0160.4
Molmo2-8BAccess Type=Molmo2 family2026.0160.2
Qwen3-VL-4BAccess Type=Open weights only2026.0158.4
Qwen3-VL-8BAccess Type=Open weights only2026.0157.6
GLM-4.1V-9BAccess Type=Open weights only2026.0156.6
VideoChat-Flash-7BAccess Type=Open models2026.0156
Molmo2-O-7BAccess Type=Molmo2 family2026.0155.2
Keye-VL-1.5-8BAccess Type=Open weights only2026.0153.8
InternVL3.5-8BAccess Type=Open weights only2026.0153.2
LLaVA-Video-7BAccess Type=Open models2026.0152.8
PLM-8BAccess Type=Open models2026.0152.6
InternVL3.5-4BAccess Type=Open weights only2026.0152
PLM-3BAccess Type=Open models2026.0148.4