Computer Science > Logic in Computer Science
[Published 2021-08-31 on arXiv; indexed on aiXiv 27 Aug 2026]
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