PyTorch vs TensorFlow

The best value in each numeric row is marked. Sponsorship has no effect on any of them.

Comparison of PyTorch vs TensorFlow
Criteria PyTorch
8 92.8 =
TensorFlow
177 73.4 =
Score 92.8 (best) 73.4
Release freshness 91.0 (best) 32.2
Adoption signals 83.6 88.4 (best)
Release freshness
Updated 60 days ago
Stale: 257 days without a release
Latest version 197412 · 2026-09-19v2.21.0 · 2026-03-06
Pricing FreeFree
License Open sourceOpen source
Platforms
Linux ✓ ✓
macOS ✓ ✓
Windows ✓ ✓
API only ✓ ✓
Features
Integrations
Rank receipt: PyTorch
#8 overall · #1 in category
92.8/100
  1. Platform readiness +40.0 100.0 × 40%
  2. Release freshness +31.8 91.0 × 35%
  3. Adoption signals +20.9 83.6 × 25%
Data from GitHub Last sync Computed on Sponsorship weight 0%, never counted Read the full formula
Rank receipt: TensorFlow
#177 overall · #5 in category
73.4/100
  1. Platform readiness +40.0 100.0 × 40%
  2. Release freshness +11.3 32.2 × 35%
  3. Adoption signals +22.1 88.4 × 25%
Data from GitHub Last sync Computed on Sponsorship weight 0%, never counted Read the full formula

Component values are before weighting. Read the full formula