List your company

Video Understanding on VideoEvalPro (test)

0.784AccuracyGemini 2.5 Pro
0.447040.534520.6220.70948Jan 15, 2026Jan 27, 2026Feb 8, 2026Feb 21, 2026Mar 5, 2026Mar 17, 2026Mar 30, 2026

Evaluation results

MethodLinks
Gemini 2.5 ProAccess Type=API call only2026.010.784
Gemini 2.5 ProCategory=API call only2026.030.784
Gemini 3 ProAccess Type=API call only2026.010.78
Gemini 3 ProCategory=API call only2026.030.78
Gemini 2.5 FlashAccess Type=API call only2026.010.696
Gemini 2.5 FlashCategory=API call only2026.030.696
GPT-5Access Type=API call only2026.010.688
GPT-5Category=API call only2026.030.688
Molmo2-8BAccess Type=Molmo2 family2026.010.604
Molmo2-8BCategory=Fully open2026.030.604
GPT-5 miniAccess Type=API call only2026.010.601
GPT-5 miniCategory=API call only2026.030.601
Molmo2-4BAccess Type=Molmo2 family2026.010.599
Molmo2-4BCategory=Fully open2026.030.599
Eagle2.5-8BAccess Type=Open weights only2026.010.586
Eagle2.5-8BCategory=Open weights2026.030.586
MolmoPoint-8BCategory=MolmoPoint2026.030.58
Molmo2-O-7BAccess Type=Molmo2 family2026.010.551
Molmo2-O-7BCategory=Fully open2026.030.551
Keye-VL-1.5-8BAccess Type=Open weights only2026.010.549
MiniCPM-V-4.5-8BAccess Type=Open weights only2026.010.549
Keye-VL-1.5-8BCategory=Open weights2026.030.549
MiniCPM-V-4.5-8BCategory=Open weights2026.030.549
VideoChat-Flash-7BAccess Type=Open models2026.010.512
VideoChat-Flash-7BCategory=Fully open2026.030.512
GLM-4.1V-9BAccess Type=Open weights only2026.010.511
GLM-4.1V-9BCategory=Open weights2026.030.511
Claude Sonnet 4.5Access Type=API call only2026.010.505
Claude Sonnet 4.5Category=API call only2026.030.505
Qwen3-VL-8BAccess Type=Open weights only2026.010.503
Qwen3-VL-8BCategory=Open weights2026.030.503
Qwen3-VL-4BAccess Type=Open weights only2026.010.498
Qwen3-VL-4BModel=Qwen3-VL-4B, Pruning Strength=None2026.030.498
Qwen3-VL-4BCategory=Open weights2026.030.498
InternVL3.5-8BAccess Type=Open weights only2026.010.481
InternVL3.5-8BModel=InternVL3.5-8B, Pruning Strength=None2026.030.481
InternVL3.5-8BCategory=Open weights2026.030.481
LLaVA-Video-7BAccess Type=Open models2026.010.478
LLaVA-Video-7BCategory=Fully open2026.030.478
STTSModel=STTS, Pruning Strength=30%2026.030.477
BaselineModel=Baseline, Pruning Strength=0%2026.030.476
PLM-8BAccess Type=Open models2026.010.472
PLM-8BModel=PLM-8B, Pruning Strength=None2026.030.472
STTSModel=STTS, Pruning Strength=40%2026.030.472
PLM-8BCategory=Fully open2026.030.472
InternVL3.5-4BAccess Type=Open weights only2026.010.465
InternVL3.5-4BCategory=Open weights2026.030.465
PLM-3BAccess Type=Open models2026.010.462
PLM-3BCategory=Fully open2026.030.462
STTSModel=STTS, Pruning Strength=50%2026.030.46