Repo Compare › Deep learning

PyTorch vs TensorFlow vs JAX

A side-by-side look at how actively PyTorch, TensorFlow and JAX are developed on GitHub — popularity, contributor base, commit activity and how quickly issues and pull requests move.

What the numbers say

Head-to-head

Snapshot taken 30 September 2026.

MetricPyTorch
Slowing
TensorFlow
Active
JAX
Active
Stars104k201k36k
Forks31k78k3.8k
Contributors7.1k5.3k1.1k
Commits, last 52 weeks18k14k7.8k
Open issues14k6471.8k
Open pull requests3.5k2.6k842
Closed / merged PRs134k80k29k
Watchers1.8k7.5k333
Last push30 Sep 202630 Sep 202630 Sep 2026
Latest releasev2.14.0 (Sep 2026)v2.21.0 (Mar 2026)jax-v0.11.2 (Sep 2026)
Main languagePythonC++Python
LicenceNot detected by GitHubApache-2.0Apache-2.0
CreatedAug 2016Nov 2015Oct 2018

Bold marks the highest value in a row. “Active / Slowing / Dormant” is a simple heuristic from how recently code was pushed and open issues per star — a starting point, not a verdict. Stars measure popularity, not quality.

Open these in the live comparer →

Related comparisons