Share your thoughts, 1 month free Claude Pro on usSee more

Video Understanding on VideoEvalPro (test)

0.784Accuracy

Gemini 2.5 Pro

Updated 18d ago

Evaluation Results

Method	Links
Gemini 2.5 Pro 2026.01		0.784
Gemini 2.5 Pro 2026.03		0.784
Gemini 3 Pro 2026.01		0.78
Gemini 3 Pro 2026.03		0.78
Gemini 2.5 Flash 2026.01		0.696
Gemini 2.5 Flash 2026.03		0.696
GPT-5 2026.01		0.688
GPT-5 2026.03		0.688
Molmo2-8B 2026.01		0.604
Molmo2-8B 2026.03		0.604
GPT-5 mini 2026.01		0.601
GPT-5 mini 2026.03		0.601
Molmo2-4B 2026.01		0.599
Molmo2-4B 2026.03		0.599
Eagle2.5-8B 2026.01		0.586
Eagle2.5-8B 2026.03		0.586
MolmoPoint-8B 2026.03		0.58
Molmo2-O-7B 2026.01		0.551
Molmo2-O-7B 2026.03		0.551
Keye-VL-1.5-8B 2026.01		0.549
MiniCPM-V-4.5-8B 2026.01		0.549
Keye-VL-1.5-8B 2026.03		0.549
MiniCPM-V-4.5-8B 2026.03		0.549
VideoChat-Flash-7B 2026.01		0.512
VideoChat-Flash-7B 2026.03		0.512
GLM-4.1V-9B 2026.01		0.511
GLM-4.1V-9B 2026.03		0.511
Claude Sonnet 4.5 2026.01		0.505
Claude Sonnet 4.5 2026.03		0.505
Qwen3-VL-8B 2026.01		0.503
Qwen3-VL-8B 2026.03		0.503
Qwen3-VL-4B 2026.01		0.498
Qwen3-VL-4B 2026.03		0.498
Qwen3-VL-4B 2026.03		0.498
InternVL3.5-8B 2026.01		0.481
InternVL3.5-8B 2026.03		0.481
InternVL3.5-8B 2026.03		0.481
LLaVA-Video-7B 2026.01		0.478
LLaVA-Video-7B 2026.03		0.478
STTS 2026.03		0.477
Baseline 2026.03		0.476
PLM-8B 2026.01		0.472
PLM-8B 2026.03		0.472
STTS 2026.03		0.472
PLM-8B 2026.03		0.472
InternVL3.5-4B 2026.01		0.465
InternVL3.5-4B 2026.03		0.465
PLM-3B 2026.01		0.462
PLM-3B 2026.03		0.462
STTS 2026.03		0.46