No known security advisories.
The current version has no OSV.dev malware reports and no critical or high-severity vulnerabilities.
torchmetrics has 12.4M monthly downloads and 2K GitHub stars. Version 1.9.0 supports Python 3.10+, first published in 2020.
It is actively maintained under a permissive license, last released in Mar 2026.
It is built on top of lightning-utilities, numpy and packaging. It is used by 574 tracked packages, including pytorch-lightning, lightning and pyannote-audio.
GitHub topics include data-science, machine-learning and pytorch.
Package Insights
Package Risks
- No releases in 93 days despite active commits
Score breakdown - each component scores 0-100, weighted by percentage
Maintenance
90
Popularity
74
Adoption
60
Community
90
Provenance
100
How the maintenance status was determined
Last commit
25 days ago
Monthly downloads
12,419,547
•
Active
Activity within 30 days
Stable
Activity within 31-180 days
Minimal
Activity within 181-365 days, or no activity data
At Risk
No activity for > 365 days, but > 10,000 monthly downloads
Archived
Repository flagged as archived on GitHub
How the popularity category was determined
Monthly downloads
12,419,547
Stars
2,445
Stars per 1k downloads
0.20
•
Industry Standard
> 10,000,000 monthly downloads
Hidden Gem
< 0.5 stars per 1k downloads and > 100,000 monthly downloads
Community Favorite
> 5 stars per 1k downloads
Rising Star
Balanced ratio of stars to downloads
Unknown
Fewer than 1,000 monthly downloads, or no star data
How download momentum is calculated
Week daily avg
371,821
Month daily avg
413,985
Momentum
-10.2%
((week_daily_avg - month_daily_avg) / month_daily_avg) * 100Python version support tiers
requires_python
>=3.10
Cutting Edge
Minimum supported version is 3.12 or newer
•
Modern
Minimum supported version is 3.9, 3.10, or 3.11
Legacy
Supports 3.8 or older (or Python 2)
Unknown
No requires_python specified or unparseable
License categories
License
Apache-2.0
•
Permissive
MIT, Apache, BSD, ISC, Unlicense, CC0, etc.
Copyleft
GPL, LGPL, AGPL, MPL, EPL, etc.
Proprietary
Commercial, all rights reserved, custom EULAs
Unknown
No license specified, or none of the above match
How the release cadence was determined
Last release
119 days ago
Total releases
86
Releases/year
15.2
•
Rapid
Last release within 365 days and > 12 releases/year
Regular
Last release within 365 days
Slow
Last release 366-730 days ago
Stalled
Last release > 730 days ago, or no releases
Unknown
No usable release date available
How contributor risk was determined
Contributors
324
Monthly downloads
12,419,547
High Load
≤ 2 contributors and ≥ 50,000 monthly downloads
Moderate Load
< 10 contributors and ≥ 500,000 monthly downloads
Low Load
< 25 contributors and ≥ 5,000,000 monthly downloads, or sole maintainer with ≥ 10,000 monthly downloads
•
Balanced
Enough contributors for the package's popularity
Unknown
No contributor data available
Engagement
95
Issue Burden
37.2
per 1k stars
Discussions
82.2
per 1k stars
Fork Ratio
65.1%
contrib / forks
Stale Release
93d
PR Velocity
Quiet
Weekly Downloads
GitHub Stars
Not all downloads include detailed metadata. Breakdowns reflect the subset that does.
Downloads by OS
Linux
202.4K
Windows
17.7K
macOS
6.9K
Python Versions
3.12
41.2%
86.4K
3.11
27.4%
57.5K
3.10
19.5%
41.0K
3.13
6.4%
13.3K
3.9
5.5%
11.5K
Top Countries
1.
US
162.1K
US
2.
SG
10.8K
SG
3.
IE
10.7K
IE
4.
DE
5.9K
DE
5.
JP
5.2K
JP
6.
CA
4.1K
CA
7.
NL
3.8K
NL
8.
CN
3.7K
CN
9.
KR
3.7K
KR
10.
IN
2.5K
IN
Dependencies
4
- lightning-utilities >=0.15.3
- numpy >1.20.0
- packaging >17.1
- torch >=2.0.0
134 optional dependencies
- aeon[dev]
- bert-score[dev]
- dists-pytorch[dev]
- dython[dev]
- einops[video]
- einops[all]
- einops[dev]
- einops[multimodal]
- fairlearn[dev]
- fast-bss-eval[dev]
- faster-coco-eval[dev]
- gammatone[dev]
- gammatone[audio]
- gammatone[all]
- huggingface-hub[dev]
- ipadic[all]
- ipadic[text]
- ipadic[dev]
- jiwer[dev]
- kornia[dev]
- librosa[dev]
- librosa[audio]
- librosa[all]
- lpips[dev]
- matplotlib[visual]
- matplotlib[all]
- matplotlib[dev]
- mecab-ko[dev]
- mecab-ko-dic[dev]
- mecab-python3[dev]
- mecab-python3[text]
- mecab-python3[all]
- mir-eval[dev]
- monai[dev]
- mypy[typing]
- mypy[all]
- mypy[dev]
- netcal[dev]
- nltk[dev]
- nltk[text]
- nltk[all]
- numpy[dev]
- onnxruntime[dev]
- onnxruntime[audio]
- onnxruntime[all]
- pandas[dev]
- permetrics[dev]
- pesq[audio]
- pesq[dev]
- pesq[all]
- piq[dev]
- piq[multimodal]
- piq[all]
- properscoring[dev]
- pycocotools[detection]
- pycocotools[dev]
- pycocotools[all]
- pystoi[audio]
- pystoi[dev]
- pystoi[all]
- pytdc[dev]
- pytorch-msssim[dev]
- regex[all]
- regex[dev]
- regex[text]
- requests[audio]
- requests[all]
- requests[dev]
- rouge-score[dev]
- sacrebleu[dev]
- scienceplots[all]
- scienceplots[visual]
- scienceplots[dev]
- scikit-image[dev]
- scipy[dev]
- scipy[image]
- scipy[all]
- sentencepiece[dev]
- sentencepiece[text]
- sentencepiece[all]
- setuptools[dev]
- sewar[dev]
- statsmodels[dev]
- timm[dev]
- timm[all]
- timm[multimodal]
- torch[dev]
- torch[typing]
- torch[all]
- torch-complex[dev]
- torch-fidelity[all]
- torch-fidelity[dev]
- torch-fidelity[image]
- torch-linear-assignment[all]
- torch-linear-assignment[clustering]
- torch-linear-assignment[dev]
- torchaudio[all]
- torchaudio[audio]
- torchaudio[dev]
- torchvision[dev]
- torchvision[all]
- torchvision[detection]
- torchvision[image]
- tqdm[all]
- tqdm[dev]
- tqdm[text]
- transformers[all]
- transformers[dev]
- transformers[multimodal]
- transformers[text]
- types-emoji[all]
- types-emoji[dev]
- types-emoji[typing]
- types-protobuf[all]
- types-protobuf[dev]
- types-protobuf[typing]
- types-pyyaml[all]
- types-pyyaml[dev]
- types-pyyaml[typing]
- types-requests[all]
- types-requests[dev]
- types-requests[typing]
- types-setuptools[all]
- types-setuptools[dev]
- types-setuptools[typing]
- types-six[all]
- types-six[dev]
- types-six[typing]
- types-tabulate[all]
- types-tabulate[dev]
- types-tabulate[typing]
- vmaf-torch[all]
- vmaf-torch[dev]
- vmaf-torch[video]
Used By
574
- pytorch-lightning
- lightning
- pyannote-audio
- autogluon-multimodal
- torchgeo
- neuralprophet
- mattersim
- mace-torch
- pytabkit
- audiocraft
- scvi-tools
- unbabel-comet
- gandlf
- terratorch
- anomalib
- mosaicml
- autotrain-advanced
- nequip
- enformer-pytorch
- nerfstudio
- super-gradients
- grelu
- poutyne
- olive-ai
- schnetpack
- memolib
- torchrec
- composer
- geobenchv2
- neuraltrain
- uniception
- kraken
- rslearn
- torchrec-nightly
- clarinpl-embeddings
- dalle2-pytorch
- ai2-olmo-eval
- openrlhf
- spotpython
- avdeepfake1m
- islp
- stable-pretraining
- dinov2
- analysisg
- birder
- pytorch-tabular
- careamics
- torchsurv
- vws-python-mock
- lightly-train
GitHub Topics
Tags from the package's GitHub repository describing what it does.
Package Information
License
Apache-2.0
First Release
November 3, 2020
Last Release
3 months ago
Last Commit
3 weeks ago
Latest Version
1.9.0
Total Releases
86
Contributors
324
Open PRs
58
Archived
No
Author
Lightning-AI et al.
Python Versions
3
3.10
3.11
3.12
Wheels
py3
Keywords
Tracking Since
January 6, 2026
Data Updated
July 5, 2026
Data Freshness
Fresh