The Best deepseek-ai/DeepSeek-Coder Alternatives in 2026

CodeGen provides open-source models for program synthesis and code generation.

OpenVLA provides an open-source vision-language-action model for robotic manipulation tasks.

This repository contains the DeepSeek-V3 language model project and related source files.

This repository contains Google Research code for the Flan-T5 language model project.

DeepSWE benchmarks coding agents on original, long-horizon software engineering tasks.

Code and documentation to train Stanford's Alpaca models, and generate the data.

Janus combines multimodal understanding and image generation models in a unified model series.

MobiLlama is a small language model designed for edge devices, according to its repository description.

Qwen3-Coder provides a code-focused model in the Qwen family of large language models.

ChatGLM-6B is an open bilingual dialogue language model described in English and Chinese.

xTuring supports personalizing open source language models through preprocessing and fine tuning.

Point·E is a research project that generates 3D point clouds using diffusion models.

timm provides PyTorch image encoders and backbones along with training, evaluation, inference, and export scripts.

The learn2learn library supports meta learning experiments and research with PyTorch.

This repository accompanies research on improving language model factuality and reasoning through multi-agent debate.

WizardLM collects language models developed with Evol-Instruct, including WizardCoder and WizardMath.

The Qwen3 model series was developed by the Qwen team at Alibaba Cloud.

Alibi explains machine learning model predictions through a set of algorithms.

ImageBind explores a shared embedding space that connects different kinds of data.

This repository implements a GPT-4 agent for playing imperfect information games with theory of mind.

The DeepSeek-R1 repository links to its reasoning research paper and provides related model materials.

DeepSeek-VL2 supports multimodal understanding through a mixture-of-experts vision-language model.

Bittensor is an open machine intelligence network where subnets produce digital commodities such as compute and inference, with contributors earning TAO.

MetaWorld provides robotics environments for benchmarking multi task and meta reinforcement learning.