MME-Benchmarks/Video-MME

✨✨[CVPR 2025] Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis

36
/ 100
Emerging

This project provides a comprehensive benchmark for evaluating how well Multi-modal Large Language Models (MLLMs) can understand and analyze video content. It takes various video types, along with their subtitles and audio, and outputs an assessment of the MLLM's ability to answer questions about the video. This is ideal for researchers and developers who are building or improving AI models that interpret video.

732 stars.

Use this if you need to rigorously test the video understanding capabilities of your AI model across diverse real-world scenarios and different video lengths.

Not ideal if you are looking for an off-the-shelf tool for video content analysis without developing or evaluating an AI model.

AI model evaluation video content analysis machine learning research multimodal AI large language model development
No License No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 12 / 25

How are scores calculated?

Stars

732

Forks

27

Language

License

Last pushed

Dec 08, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/MME-Benchmarks/Video-MME"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.