Alternatives and similar repositories for DeepSeek-Prover-V2

Users that are interested in DeepSeek-Prover-V2 are comparing it to the libraries listed below

• deepseek-ai / DeepSeek-Math-V2
  ☆1,515Updated last month
• deepseek-ai / DeepSeek-Prover-V1.5
  ☆551Updated last year
• microsoft / rStar
  ☆1,377Updated 3 months ago
• aw31 / openai-imo-2025-proofs
  ☆482Updated 5 months ago
• deepseek-ai / DeepSeek-V3.2-Exp
  ☆1,405Updated last month
• openai / frontier-evals
  OpenAI Frontier Evals
  ☆974Updated last month
• MoonshotAI / Kimina-Prover-Preview
  Technical report of Kimina-Prover Preview.
  ☆350Updated 6 months ago
• MoonshotAI / Moonlight
  Muon is Scalable for LLM Training
  ☆1,397Updated 5 months ago
• safety-research / circuit-tracer
  ☆2,529Updated this week
• ByteDance-Seed / Seed-Prover
  ☆395Updated 3 weeks ago
• lyang36 / IMO25
  An AI agent system for solving International Mathematical Olympiad (IMO) problems using Google's Gemini, OpenAI, and XAI APIs.
  ☆899Updated 3 months ago
• DreamLM / Dream
  Dream 7B, a large diffusion language model
  ☆1,139Updated last month
• rllm-org / rllm
  Democratizing Reinforcement Learning for LLMs
  ☆4,942Updated last week
• centerforaisafety / hle
  Humanity's Last Exam
  ☆1,294Updated 3 months ago
• sail-sg / understand-r1-zero
  Understanding R1-Zero-Like Training: A Critical Perspective
  ☆1,181Updated 4 months ago
• GAIR-NLP / LIMO
  [COLM 2025] LIMO: Less is More for Reasoning
  ☆1,059Updated 5 months ago
• facebookresearch / coconut
  Training Large Language Model to Reason in a Continuous Latent Space
  ☆1,430Updated 4 months ago
• MiniMax-AI / MiniMax-M1
  MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.
  ☆3,032Updated 6 months ago
• openai / harmony
  Renderer for the harmony response format to be used with gpt-oss
  ☆4,124Updated 3 weeks ago
• open-thought / reasoning-gym
  [NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards
  ☆1,296Updated 3 weeks ago
• seal-rg / recurrent-pretraining
  Pretraining and inference code for a large-scale depth-recurrent language model
  ☆857Updated last week
• XiaomiMiMo / MiMo
  MiMo: Unlocking the Reasoning Potential of Language Model – From Pretraining to Posttraining
  ☆1,896Updated 7 months ago
• policy-gradient / GRPO-Zero
  Implementing DeepSeek R1's GRPO algorithm from scratch
  ☆1,729Updated 8 months ago
• SkyworkAI / Skywork-OR1
  Unleashing the Power of Reinforcement Learning for Math and Code Reasoners
  ☆737Updated 7 months ago
• ByteDance-Seed / Seed-Coder
  Seed-Coder is a family of lightweight open-source code LLMs comprising base, instruct and reasoning models, developed by ByteDance Seed.
  ☆722Updated 7 months ago
• MoonshotAI / Kimi-Linear
  ☆1,257Updated last month
• project-numina / aimo-progress-prize
  ☆478Updated last year
• natolambert / rlhf-book
  Textbook on reinforcement learning from human feedback
  ☆1,396Updated this week
• MiniMax-AI / MiniMax-01
  The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model & vision-language-model based on Linear Attention
  ☆3,290Updated 6 months ago
• PrimeIntellect-ai / prime-rl
  Async RL Training at Scale
  ☆985Updated this week