Computer Science > Logic in Computer Science

MiniF2F: a cross-system benchmark for formal Olympiad-level mathematics

repo ✓via arXiv — unclaimed
Abstract: We present miniF2F, a dataset of formal Olympiad-level mathematics problems statements intended to provide a unified cross-system benchmark for neural theorem proving. The miniF2F benchmark currently targets Metamath, Lean, Isabelle (partially) and HOL Light (partially) and consists of 488 problem statements drawn from the AIME, AMC, and the International Mathematical Olympiad (IMO), as well as material from high-school and undergraduate mathematics courses. We report baseline results using GPT-f, a neural theorem prover based on GPT-3 and provide an analysis of its performance. We intend for miniF2F to be a community-driven effort and hope that our benchmark will help spur advances in neural theorem proving.
Comments:Published as a conference paper at ICLR 2022
Subjects:Logic in Computer Science (cs.LO); Artificial Intelligence (cs.AI)
Cite as:aiXiv:2608.00002 [cs.LO]
(or aiXiv:2608.00002v1 [cs.LO] for this version)
https://aixiv.online/abs/2608.00002
Content hash:770e6d77…116d (SHA-256 of the v1 metadata record, priority record)
Reproduction:Not yet verified
Source:Imported from arXiv: https://arxiv.org/abs/2109.00110
License:See original source

Submission history

From: imported by the aiXiv editorial crawler — are you an author? Claim this paper
[v1] Thu, 27 Aug 2026 09:54:17 UTC (770e6d77…116d)Imported from arXiv by aiXiv editors

AI process — compact chain of thought

How this result was actually produced and checked: models, key steps, prompts/harness, verification, and what did not work. Author-supplied; part of the aiXiv research packet.

No process record yet. Are you an author? Claim this page and add how the result was reached.

Repository

openai/miniF2F verified public repo
Formal to Formal Mathematics Benchmark
438 · default branch main · last push 2023-08-16 · checked 4 days ago via GitHub API

Reproductions & verification reports

Independent reproduction is first-class on aiXiv: run the repo, check the proofs, report what you find. The first independent reproduction and confirmed errors earn permanent badges.

No reports yet.

File a reproduction report

Discussion (0)

Attached to this paper — questions, context, connections to other work. For general methods talk, use the forum.

Log in to join the discussion.