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
  ☆1,490Updated 2 weeks ago
• microsoft / rStar
  ☆1,357Updated 3 months ago
• deepseek-ai / DeepSeek-Prover-V1.5
  ☆547Updated last year
• aw31 / openai-imo-2025-proofs
  ☆479Updated 5 months ago
• openai / frontier-evals
  OpenAI Frontier Evals
  ☆962Updated 2 weeks ago
• deepseek-ai / DeepSeek-V3.2-Exp
  ☆1,367Updated last month
• MoonshotAI / Kimina-Prover-Preview
  Technical report of Kimina-Prover Preview.
  ☆348Updated 5 months ago
• ByteDance-Seed / Seed-Prover
  ☆324Updated 3 months ago
• lyang36 / IMO25
  An AI agent system for solving International Mathematical Olympiad (IMO) problems using Google's Gemini, OpenAI, and XAI APIs.
  ☆884Updated 2 months ago
• centerforaisafety / hle
  Humanity's Last Exam
  ☆1,267Updated 2 months ago
• MoonshotAI / Kimi-Linear
  ☆1,233Updated last month
• SakanaAI / ShinkaEvolve
  ShinkaEvolve: Towards Open-Ended and Sample-Efficient Program Evolution
  ☆745Updated last week
• DreamLM / Dream
  Dream 7B, a large diffusion language model
  ☆1,104Updated last month
• project-numina / aimo-progress-prize
  ☆477Updated last year
• safety-research / circuit-tracer
  ☆2,489Updated last month
• MoonshotAI / Moonlight
  Muon is Scalable for LLM Training
  ☆1,380Updated 4 months ago
• GAIR-NLP / LIMO
  [COLM 2025] LIMO: Less is More for Reasoning
  ☆1,056Updated 4 months ago
• seal-rg / recurrent-pretraining
  Pretraining and inference code for a large-scale depth-recurrent language model
  ☆855Updated 2 months ago
• policy-gradient / GRPO-Zero
  Implementing DeepSeek R1's GRPO algorithm from scratch
  ☆1,712Updated 8 months ago
• sail-sg / understand-r1-zero
  Understanding R1-Zero-Like Training: A Critical Perspective
  ☆1,173Updated 3 months ago
• Goedel-LM / Goedel-Prover
  ☆220Updated 8 months ago
• rllm-org / rllm
  Democratizing Reinforcement Learning for LLMs
  ☆4,854Updated this week
• MiniMax-AI / MiniMax-M1
  MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.
  ☆3,002Updated 5 months ago
• natolambert / rlhf-book
  Textbook on reinforcement learning from human feedback
  ☆1,354Updated last week
• google-deepmind / alphaevolve_results
  ☆247Updated 6 months ago
• SkyworkAI / Skywork-OR1
  Unleashing the Power of Reinforcement Learning for Math and Code Reasoners
  ☆734Updated 6 months ago
• teorth / estimates
  Code to automatically prove or verify estimates in analysis
  ☆319Updated 5 months ago
• arcprize / ARC-AGI-2
  ☆586Updated 6 months ago
• laude-institute / terminal-bench
  A benchmark for LLMs on complicated tasks in the terminal
  ☆1,235Updated this week
• facebookresearch / cwm
  Research code artifacts for Code World Model (CWM) including inference tools, reproducibility, and documentation.
  ☆769Updated 2 months ago