数学研究问题基准测试

BuddenBench 是一个用于评估模型和智能体自主解决开放数学研究问题能力的基准测试,包含来自群论、几何、分析等领域的问题,并支持使用 GAP 和 Lean 4 等工具进行形式化验证。

  • by maxvonhippel
  • Lean
  • 本地部署
  • 3 星标
  • 更新于
在 GitHub 查看 maxvonhippel/group-theory-benchmark

使用说明

🔮 BuddenBench: A Benchmark of Open Nontrivial Mathematics Research Problems

This benchmark, affectionately named budden-bench, measures the ability of models and agents to autonomously solve open and important problems in mathematics research. In contrast to other problem sets such as the Erdős Problems, this benchmark is intended to exclusively contain problems which are of ongoing research interest to working mathematicians.

Inspiration

This project was inspired by the historical successes of mathematical software for resolving open conjectures, pre-LLM.

Tools

AI-Generated Solutions

Warning: No AI-generated proof should be trusted without human review, no matter how formal.

Legend: 🟢 Success | 🔴 Cannot formalize | 🟡 Unverified | 🟣 New result | ⚪ Unknown

Problem List Artifact Status Human Review
1 green formalization.lean 🟢 Formalized (unsolved) Pending
10 green cannot_formalize.txt 🔴 Cannot formalize Pending
100 green cannot_formalize.txt 🔴 Cannot formalize Pending
11 green cannot_formalize.txt 🔴 Cannot formalize Pending
12 green formalization.lean 🟢 Formalized (unsolved) Pending
13 green cannot_formalize.txt 🔴 Cannot formalize Pending
14 green formalization.lean 🟢 Formalized (unsolved) Pending
15 green formalization.lean 🟢 Formalized (unsolved) Pending
16 green formalization.lean 🟢 Formalized (unsolved) Pending
17 green cannot_formalize.txt 🔴 Cannot formalize Pending
18 green formalization.lean 🟢 Formalized (unsolved) Pending
19 green formalization.lean 🟢 Formalized (unsolved) Pending
2 green formalization.lean 🟢 Formalized (unsolved) Pending
20 green cannot_formalize.txt 🔴 Cannot formalize Pending
21 green formalization.lean 🟢 Formalized (unsolved) Pending
22 green formalization.lean 🔴 Cannot formalize Pending
23 green formalization.lean 🟢 Formalized (unsolved) Pending
24 green formalization.lean 🟢 Formalized (unsolved) Pending
25 green cannot_formalize.txt 🔴 Cannot formalize Pending
26 green formalization.lean 🟢 Formalized (unsolved) Pending
27 green cannot_formalize.txt 🔴 Cannot formalize Pending
28 green formalization.lean 🟢 Formalized (unsolved) Pending
29 green formalization.lean 🟢 Formalized (unsolved) Pending
3 green formalization.lean 🟢 Formalized (unsolved) Pending
30 green cannot_formalize.txt 🔴 Cannot formalize Pending
31 green cannot_formalize.txt 🔴 Cannot formalize Pending
32 green formalization.lean 🟢 Formalized (unsolved) Pending
33 green formalization.lean 🟢 Formalized (unsolved) Pending
34 green cannot_formalize.txt 🔴 Cannot formalize Pending
35 green formalization.lean 🟢 Formalized (unsolved) Pending
36 green formalization.lean 🟢 Formalized (unsolved) Pending
37 green cannot_formalize.txt 🔴 Cannot formalize Pending
38 green formalization.lean 🟢 Formalized (unsolved) Pending
39 green formalization.lean 🟢 Formalized (unsolved) Pending
4 green formalization.lean 🟢 Formalized (unsolved) Pending
40 green formalization.lean 🟢 Formalized (unsolved) Pending
41 green cannot_formalize.txt 🔴 Cannot formalize Pending
42 green cannot_formalize.txt 🔴 Cannot formalize Pending
43 green formalization.lean 🟢 Formalized (unsolved) Pending
44 green formalization.lean 🟢 Formalized (unsolved) Pending
45 green formalization.lean 🟢 Formalized (unsolved) Pending
46 green formalization.lean 🟢 Formalized (unsolved) Pending
47 green formalization.lean 🟢 Formalized (unsolved) Pending
48 green cannot_formalize.txt 🔴 Cannot formalize Pending
49 green formalization.lean 🟢 Formalized (unsolved) Pending
5 green cannot_formalize.txt 🔴 Cannot formalize Pending
50 green formalization.lean 🟢 Formalized (unsolved) Pending
51 green cannot_formalize.txt 🔴 Cannot formalize Pending
52 green formalization.lean 🟢 Formalized (unsolved) Pending
53 green formalization.lean 🟢 Formalized (unsolved) Pending
54 green formalization.lean 🟢 Formalized (unsolved) Pending
55 green cannot_formalize.txt 🔴 Cannot formalize Pending
56 green cannot_formalize.txt 🔴 Cannot formalize Pending
57 green formalization.lean 🟢 Formalized (unsolved) Pending
58 green cannot_formalize.txt 🔴 Cannot formalize Pending
59 green cannot_formalize.txt 🔴 Cannot formalize Pending
6 green formalization.lean 🟢 Formalized (unsolved) Pending
60 green formalization.lean 🟢 Formalized (unsolved) Pending
61 green cannot_formalize.txt 🔴 Cannot formalize Pending
62 green formalization.lean 🟢 Formalized (unsolved) Pending
63 green formalization.lean 🟢 Formalized (unsolved) Pending
64 green formalization.lean 🟢 Formalized (unsolved) Pending
65 green formalization.lean 🟢 Formalized (unsolved) Pending
66 green formalization.lean 🟢 Formalized (unsolved) Pending
67 green cannot_formalize.txt 🔴 Cannot formalize Pending
68 green cannot_formalize.txt 🔴 Cannot formalize Pending
69 green formalization.lean 🟢 Formalized (unsolved) Pending
7 green formalization.lean 🟢 Formalized (unsolved) Pending
70 green formalization.lean 🟢 Formalized (unsolved) Pending
71 green cannot_formalize.txt 🔴 Cannot formalize Pending
72 green formalization.lean 🟢 Formalized (unsolved) Pending
73 green formalization.lean 🟢 Formalized (unsolved) Pending
74 green cannot_formalize.txt 🔴 Cannot formalize Pending
75 green formalization.lean 🟢 Formalized (unsolved) Pending
76 green formalization.lean 🟢 Formalized (unsolved) Pending
77 green cannot_formalize.txt 🔴 Cannot formalize Pending
78 green formalization.lean 🟢 Formalized (unsolved) Pending
79 green cannot_formalize.txt 🔴 Cannot formalize Pending
8 green cannot_formalize.txt 🔴 Cannot formalize Pending
80 green cannot_formalize.txt 🔴 Cannot formalize Pending
81 green cannot_formalize.txt 🔴 Cannot formalize Pending
82 green cannot_formalize.txt 🔴 Cannot formalize Pending
83 green cannot_formalize.txt 🔴 Cannot formalize Pending
84 green cannot_formalize.txt 🔴 Cannot formalize Pending
85 green formalization.lean 🟢 Formalized (unsolved) Pending
86 green formalization.lean 🟢 Formalized (unsolved) Pending
87 green cannot_formalize.txt 🔴 Cannot formalize Pending
88 green cannot_formalize.txt 🔴 Cannot formalize Pending
89 green cannot_formalize.txt 🔴 Cannot formalize Pending
9 green cannot_formalize.txt 🔴 Cannot formalize Pending
90 green cannot_formalize.txt 🔴 Cannot formalize Pending
91 green cannot_formalize.txt 🔴 Cannot formalize Pending
92 green cannot_formalize.txt 🔴 Cannot formalize Pending
93 green formalization.lean 🟢 Formalized (unsolved) Pending
94 green formalization.lean 🟢 Formalized (unsolved) Pending
95 green formalization.lean 🟢 Formalized (unsolved) Pending
96 green cannot_formalize.txt 🔴 Cannot formalize Pending
97 green cannot_formalize.txt 🔴 Cannot formalize Pending
98 green cannot_formalize.txt 🔴 Cannot formalize Pending
99 green cannot_formalize.txt 🔴 Cannot formalize Pending
K-13 klee formalization.lean 🟢 Formalized (unsolved) Pending
K-16 klee formalization.lean 🟢 Formalized (unsolved) Pending
K-19 klee cannot_formalize.txt 🔴 Cannot formalize Pending
K-2 klee formalization.lean 🟢 Formalized (unsolved) Pending
K-22 klee cannot_formalize.txt 🔴 Cannot formalize Pending
K-4 klee formalization.lean 🟢 Formalized (unsolved) Pending
K-8 klee formalization.lean 🟢 Formalized (unsolved) Pending
K1 klee formalization.lean 🟢 Formalized (unsolved) Pending
K10 klee formalization.lean 🟢 Formalized (unsolved) Pending
K12 klee cannot_formalize.txt 🔴 Cannot formalize Pending
K14 klee formalization.lean 🟢 Formalized (unsolved) Pending
K18 klee formalization.lean 🔴 Cannot formalize Pending
K23 klee cannot_formalize.txt 🔴 Cannot formalize Pending
K3 klee formalization.lean 🟢 Formalized (unsolved) Pending
K4 klee formalization.lean 🟢 Formalized (unsolved) Pending
K5 klee formalization.lean 🟢 Formalized (unsolved) Pending
K6 klee formalization.lean 🟢 Formalized (unsolved) Pending
K7 klee formalization.lean 🟢 Formalized (unsolved) Pending
K9 klee formalization.lean 🟢 Formalized (unsolved) Pending
1.12 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
1.20 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
1.27 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
1.28 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
1.3 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
1.31 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
1.33 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
1.35 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
1.40 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
1.46 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
1.5 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
1.51 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
1.54 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
1.55 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
1.6 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
1.67 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
1.74 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
1.86 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
1.87 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
11.44 kourovka problem.lean 🟢 Formalized (unsolved) Pending
16.44 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
19.110 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
2.22 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
2.24 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
2.40 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
2.42 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
2.45 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
2.48 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
2.6 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
2.68 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
2.78 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
2.9 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
3.12. (Well-known problem) kourovka formalization.lean 🟢 Formalized (unsolved) Pending
3.16 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
3.38 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
3.43 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
3.44 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
3.46 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
3.47 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
3.48 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
3.49 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
3.5 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
3.55 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
3.57 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
3.60 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
4.17 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
4.24 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
4.40 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
4.42 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
4.46 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
4.55 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
4.56 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
4.65 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
4.66 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
4.72 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
4.75 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
5.14 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
5.25 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
5.27 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
5.30 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
5.36 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
5.38 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
5.39 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
5.42 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
5.44 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
5.5 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
5.54 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
6.10 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
6.26 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
6.30 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
6.39 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
6.5 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
6.59 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
6.62 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
6.9 kourovka cannot_formalize.txt 🟢 Formalized (unsolved) Pending
7.21 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
7.23 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
7.25 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
7.27 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
7.28 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
7.3 kourovka formalization.lean 🟢 Formalized (unsolved) Pending
7.5 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
9.9 kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
Well-known problem kourovka cannot_formalize.txt 🔴 Cannot formalize Pending
10.1 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
10.2 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
10.3 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
10.4 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
3.1 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
3.11 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
3.12 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
3.13 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
3.3 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
3.4 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
3.5 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
3.6 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
3.8 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
3.9 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
4.1 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
4.2 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
4.3 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
4.4 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
4.5 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
4.7 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
5.11 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
5.12 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
5.13 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
5.14 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
5.15 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
5.16 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
5.17 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
5.18 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
5.19 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
5.20 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
5.21 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
5.22 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
5.23 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
5.24 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
5.3 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
5.4 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
5.5 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
5.6 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
5.7 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
5.9 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
6.1 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
6.5 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
6.6 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
6.7 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
6.8 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
7.1 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
7.2 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
7.3 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
7.4 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
7.5 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
7.7 mazya formalization.lean 🟢 Formalized (unsolved) Pending
7.8 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
8.1 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
8.2 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
8.3 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
8.4 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
8.5 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
9.1 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
9.3 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
9.4 mazya cannot_formalize.txt 🔴 Cannot formalize Pending
1 ramm cannot_formalize.txt 🔴 Cannot formalize Pending
2 ramm cannot_formalize.txt 🔴 Cannot formalize Pending
3.1 ramm cannot_formalize.txt 🔴 Cannot formalize Pending
3.2 ramm cannot_formalize.txt 🔴 Cannot formalize Pending
4 ramm cannot_formalize.txt 🔴 Cannot formalize Pending

Setup

make setup  # Install dependencies, build GAP, setup Lean

Usage

make watch-solve  # Launch Claude to solve a random problem
make test         # Run test suite

Problem Sets

Problems are drawn from multiple sources:

Citation

If you use this benchmark in your research, please cite:

@dataset{vonhippel2025budden,
  author={von Hippel, Max},
  title={{BuddenBench}: A Benchmark of Open Nontrivial Mathematics Research Problems},
  year={2025},
  publisher={GitHub},
  howpublished={\url{https://github.com/maxvonhippel/budden-bench}},
  note={AI benchmark for automated mathematics research in group theory and geometry}
}

For citations to the source problem collections, see references.bib.

Last updated: 2026-01-29 05:59:25 UTC