MSU Mobile Video Codecs Benchmark
Video group head: Dr. Dmitriy Vatolin
Measurements, analysis:
Roman Kazantsev
Find the most power-efficient video-decoder on your Android device

Smart video-decoder selection to increase video playback duration on Xiaomi Mi A2 Lite and LG X Power smartphones.
See methodology for more information.
What’s New
- October 1, 2021 Beta-version Release
Key Features of the Benchmark
- Speed and power efficiency measurement. The benchmark estimates key indicators (power efficiency and speed) to find the best mobile video-decoder on a given Android device
- Video playback time increase by up to 22 hours. Use of video-decoder we recommend prolongs offline video playback duration by up to 22 hours
- 147 Android models, 6 compression standards. The benchmark ranking supports the biggest number of Android devices and contains 147 models, six compression standards (MPEG-4, H.264, VP8, VP9, HEVC, and AV1), and three resolutions (SD, HD, and Full HD)
Mobile Video-Decoder Ranking
See the full ranking for SD resolution that contains 147 device models.
See the full ranking for HD resolution that contains 147 device models.
See the full ranking for Full HD resolution that contains 147 device models.
How to Benchmark New Device
The basic rules to the benchmarking:
- In order to get the benchmarking started, the device must have battery charge between 85% and 95%
- The device must not be used during the benchmarking so it is recommended to run the test at night time during sleep



Perform the following steps to benchmark:
- Install the benchmark.
- Charge the device battery from 85% up to 95% and launch the application.
- If the first testing cycle, click the button START, type your nickname and click a button NEXT to start the testing. Otherwise, click a button CONTINUE.
- Do not use the device while the test is running. The test will take about 6–8 hours. Once the testing is complete the application displays a table with the current results.
- Go back to the main menu. If the main menu contains a button CONTINUE, the testing is not complete for all video-decoders and you need to proceed to step 2 for the next testing cycle. Otherwise, the testing is complete and you can click VIEW RESULTS to see the whole results.
Also, you can download the benchmark via this QR code:

Cite Us
To refer to our benchmark in your work, cite our paper:
@INPROCEEDINGS{
author={Kazantsev, Roman and Yanushkovsky, Vladimir and Vatolin, Dmitriy},
booktitle={2021 Data Compression Conference (DCC)},
title={Video-Decoder Power Consumption on Android Devices: Power-Estimation Method, Dataset Creation, and Analysis Results},
year={2021},
pages={347-347},
doi={10.1109/DCC50243.2021.00084}
}
|
Contact Us
For questions and proposals, please contact us: mvc-benchmark@videoprocessing.ai
See Also
VQA Dataset
During our work we have created the database for video quality assessment with subjective scores
MSU Video Upscalers Benchmark 2022
The most extensive comparison of video super-resolution (VSR) algorithms by subjective quality
MSU Video Deblurring Benchmark 2022
Learn about the best video deblurring methods and choose the best model
Site structure
-
MSU Benchmark Collection
- MSU Video Upscalers Benchmark 2022
- MSU Video Deblurring Benchmark 2022
- MSU Video Frame Interpolation Benchmark 2022
- MSU HDR Video Reconstruction Benchmark 2022
- MSU Super-Resolution for Video Compression Benchmark 2022
- MSU No-Reference Video Quality Metrics Benchmark 2022
- MSU Full-Reference Video Quality Metrics Benchmark 2022
- MSU Video Alignment and Retrieval Benchmark
- MSU Mobile Video Codecs Benchmark 2021
- MSU Video Super-Resolution Benchmark
- MSU Shot Boundary Detection Benchmark 2020
- MSU Deinterlacer Benchmark
- The VideoMatting Project
- Video Completion
- Codecs Comparisons & Optimization
- VQMT
- MSU Datasets Collection
- Metrics Research
- Video Quality Measurement Tool 3D
- Video Filters
- Other Projects