Datasets › RLM25

RLM25 (Research-Level Mathematics 2025)

Introduced by Auguste Poiroux et al. in Improving Autoformalization using Type Checking11 Feb 2025 archive 2025-07-28

RLM25 is an evaluation benchmark containing 619 paired examples of research-level natural language mathematical statements and their corresponding Lean formalizations. The examples are drawn from six real-world formalization projects, and each entry includes essential context along with timestamp information to ensure freshness and avoid data contamination. Its primary purpose is to serve as a challenging testbed for assessing autoformalization systems, helping researchers measure improvements in translating complex, research-level mathematics into formal code.

Benchmarks archive 2025-07-28

No leaderboard in the archive resolves to this dataset.

Papers archive 2025-07-28

No paper in the archive has a leaderboard row on this dataset; the archive counts 1 paper for it but never published that list.

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

License archive 2025-07-28

No licence recorded in the archive. Absence here is not a statement about the dataset's terms.

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • RLM25

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections