# ProofNet

ProofNet is an AI benchmark; this page records what it measures and traces its data, grader, and scores to primary sources.

Tests autoformalization and formal proving of undergraduate mathematics in Lean from natural-language statements.

## Details

- Address: Online, Global
- Website: [github.com/zhangir-azerbayev/ProofNet](<https://github.com/zhangir-azerbayev/ProofNet>)
- Tags: Helpful, Science
- Category: Math
- Status: Active
- Data licence: MIT
- Data access: open
- Grader: unit-test
- Organization: ProofNet authors
- Released: 2022-04
- Paper: [arxiv.org/abs/2302.12433](<https://arxiv.org/abs/2302.12433>)
- Repository: [github.com/zhangir-azerbayev/ProofNet](<https://github.com/zhangir-azerbayev/ProofNet>)
- Task count: 371
- Top-score provenance: unknown
- ABI family: No

## Questions

### Where is ProofNet?

ProofNet is at Online, Global.

### How do I contact ProofNet?

To contact ProofNet, visit https://github.com/zhangir-azerbayev/ProofNet.

## Source

From [Benchmark primary sources](https://aibenchmarkindex.com/about), license CC0-1.0, checked 2026-10-15.

Last updated October 15, 2026.

## Links

- This benchmark on the [web page](<https://aibenchmarkindex.com/global/online/proofnet>)
- [Math in Online](<https://aibenchmarkindex.com/global/online/category/math.md>)
- [More benchmarks in Online](<https://aibenchmarkindex.com/global/online.md>)

> **Check before you compare.** Benchmark methods and leaderboards change. Follow the cited primary source before using a result in a decision.