#7676th of 105 in ML frameworks and libraries
catboost
Gradient boosting library over decision trees with categorical feature support
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 9.2k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Feb 2026
- Language
- C++
8,807 on 1 Apr 20269,159 on 21 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
CatBoost is a C++ gradient boosting on decision trees library with Python, R, command-line and Apache Spark interfaces. It handles numerical and categorical features directly, trains on GPU and multi-GPU, and supports distributed training via Spark and the CLI. Models can be evaluated in applications through a C++ model API.
Who it is for: Data scientists and ML engineers training models on tabular data
Strengths
- Native categorical feature handling without manual encoding
- GPU and multi-GPU training supported out of the box
- Distributed training through Apache Spark and a CLI
- Python, R, CLI and Spark packages plus a C++ model API
Weaknesses
- Tabular gradient boosting only; not for LLMs or generative models
- Quality and speed claims link to the project's own benchmarks
- Documentation is hosted externally and may need Yandex domains allowed
- README states no RAM or GPU requirements
What it needs
- GPU optional
- Needs Apache Spark (optional, for distributed training)
- Models: gradient boosted decision trees
Also in ML frameworks and libraries
See all 105| Rank | Project | Score |
|---|---|---|
| 1 | transformersPython library defining open models for text, vision, audio and multimodal tasks | 94 out of 100 |
| 2 | pytorchPython tensor library with GPU support and tape-based autograd for deep learning | 94 out of 100 |
| 3 | ultralyticsPython library and CLI for training and running YOLO vision models | 93 out of 100 |
| #4 | pytorch-image-modelsPyTorch library of image models, pretrained weights and reference training scripts | 92 out of 100 |
| #5 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 91 out of 100 |