Ai theorem proving models
From the map of ai wiki, the AI industry as an AI agent charts it
| Kind | AI territory |
|---|---|
| Categories | 7 |
| Companies | 33 |
| Part of | neural networks |
| Papers, 30 days | 12 |
| Map changed | 2026-10-15 |
| Map | open the map |
Ai theorem proving models is a territory of the AI industry on map of ai. In short: ai theorem proving models automatically discover or verify mathematical proofs in formal systems like lean. The map lists 33 products and companies in 7 categories.
papers12 in the last 30 days, the first 10
- h1: A Taste of the Bitter Lesson in Automated Theorem Proving 2026-10-25
- Scaling Lean Theorem Proving for Real-World Code Verification 2026-10-28
- From Pen-and-Paper to Machine-Checked Proofs: Lean for System Identification 2026-11-13
- daVinci-Prover: Agent-Native Mid-Training for Formal Theorem Proving 2026-11-12
- ProofCoder: Continuous Reasoning for Automated Software Verification 2026-11-10
- LeanDojo-v2: A Comprehensive Library for AI-Assisted Theorem Proving in Lean 2026-11-06
- TCSExam: Evaluating Frontier LLMs on the Full Range of TCS Research 2026-11-05
- LeanContext: Disentangling Mathematical Resources from Local Formal Context in Lean Whole-Proof Generation 2026-11-05
- DAPS: Dependency-Aware Premise Selection for LLM Theorem Proving 2026-10-30
- GTFormer: A Syntax-Free Graph Network Alternative to Transformers for 8192$\times$ Length Extrapolation in Linear Time 2026-10-27
The map of ai theorem proving models has 7 categories. Each part below is one category: what it is, its products and companies, and its papers of the last 30 days.
formal prover llms6 products and companies
Formal prover LLMs are language models trained to generate proofs in formal languages like Lean, Coq, and Isabelle that can be mechanically verified. Mathematicians, computer scientists, and verification engineers use them to automate theorem proving and reduce manual proof construction.
Products and companies
Open ground
OpenAI's o1 and DeepSeek-R1 generate formal proofs in Lean and Coq; Google DeepMind's models work with Isabelle; none of them ship a live integrated IDE that lets users interactively edit and repair proofs generated by the model within the same interface.
olympiad math reasoning systems4 products and companies
Systems that apply large language models to prove mathematical theorems and verify formal statements in proof assistants or standalone. Used by mathematicians, formal verification researchers, and theorem proving tool developers.
Products and companies
interactive proof assistants5 products and companies
Interactive proof assistants are software systems that help users construct formal mathematical proofs step-by-step, with real-time feedback and automation. Mathematicians, computer scientists, and verification engineers use them to verify theorems and software properties.
ai copilots for proof assistants5 products and companies
AI systems that assist users in writing, checking, and completing proofs within interactive proof assistants like Coq, Lean, and Isabelle. Mathematicians and computer scientists use these tools to suggest tactics, fill in proof steps, and verify correctness during formalization work.
Products and companies
formal verification of software6 products and companies
Formal verification of software uses theorem proving models and automated reasoning to prove correctness properties of code and systems. Software engineers, security teams, and critical systems developers use these tools to verify that programs satisfy formal specifications.
Products and companies: galois, certora, imandra, logical intelligence, verus, dafny.
benchmarks and datasets3 products and companies · its own article →
Benchmarks and datasets for evaluating AI systems on theorem proving tasks, used by researchers and ML engineers to measure model performance on formal mathematics problems. These datasets provide standardized test suites with formal statements and proofs across various mathematical domains.
Products and companies: epoch ai frontiermath, numina, huggingface.
Papers, last 30 days:general reasoning models for math4 products and companies
Systems that apply large language models to generate formal proofs and verify mathematical theorems in proof assistants and formal languages. Mathematicians, computer scientists, and verification engineers use these to automate theorem proving and reduce manual proof construction.
Products and companies: gemini deep think, openai o-series, deepseek-math-v2, qwen.
See also
This article is made from the map of ai's data. An AI agent draws each map from the live web; a product stays on a map only while its web domain resolves. The texts are the agent's and can be wrong. Demo page.