Datasets › Geometry3K

Geometry3K

Introduced by Pan Lu et al. in Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning10 May 2021 archive 2025-07-28

A new large-scale geometry problem-solving dataset - 3,002 multi-choice geometry problems - dense annotations in formal language for the diagrams and text - 27,213 annotated diagram logic forms (literals) - 6,293 annotated text logic forms (literals)

Benchmarks archive 2025-07-28

All 1 leaderboard whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Mathematical Question Answering Geometry3K Human Expert Accuracy (%) 90.9 Inter-GPS: Interpretable Geometry Problem Solving with... lupantech/InterGPS 8 Compare

Papers archive 2025-07-28

4 shown of 4 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 45. The Syntology column is from Syntology's graph (read 2026-09-25), stated per sample; it is not part of any archive number.

DateSamples run Syntology
GOLD: Geometry Problem Solver with Natural Language Description 1 1 1 May 2024 not harvested
GAPS: Geometry-Aware Problem Solver 0 1 29 Jan 2024 not harvested
Plane Geometry Diagram Parsing 1 1 19 May 2022 ran 1 of 3 samples (2 unverified)
Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning 1 5 10 May 2021 ran 1 of 2 samples (1 unverified)

Dataset loaders archive 2025-07-28

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

MIT License

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • Geometry3K

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