LPBench: A Lean Benchmark for Research-Level Mathematical Theorem Proving
Year: 2026
Type: preprint
Abstract: In October 2026, OpenAI released hundreds of manuscripts resolving open mathematical problems, without publishing the full set of problems attempted by its model. Assessing the broader capabilities and limitations of such systems calls for independent benchmarks. To this end, we introduce LPBench, a benchmark for research-level mathematics comprising 117 problems formalised in Lean 4, primarily in combinatorics and graph theory. As a first application, we evaluate Claude Opus 5.5 and Claude Fable 5.1, each with and without web search. Website: https://lp-bench.github.io/
Institutions: TU Bergakademie Freiberg, Universität Hamburg
Language: English
Subfield: Computational Theory and Mathematics
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7226040197
