Datasets › TheoremQA
TheoremQA
We propose the first question-answering dataset driven by STEM theorems. We annotated 800 QA pairs covering 350+ theorems spanning across Math, EE&CS, Physics and Finance. The dataset is collected by human experts with very high quality. We provide the dataset as a new benchmark to test the limit of large language models to apply theorems to solve challenging university-level questions. We provide a pipeline in the following to prompt LLMs and evaluate their outputs with WolframAlpha.
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) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| Natural Questions | TheoremQA | GPT-4 (PoT) Accuracy 52.4 | TheoremQA: A Theorem-driven Question Answering dataset | wenhuchen/theoremqa | 19 | Compare |
Papers archive 2025-07-28
2 shown of 2 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 40. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.
| Date | Samples run Syntology | |||
|---|---|---|---|---|
| DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving | 1 | 8 | 18 Jun 2024 | ran 10 of 12 samples (2 unverified) |
| TheoremQA: A Theorem-driven Question Answering dataset | 1 | 11 | 21 May 2023 | ran 2 of 10 samples (8 unverified) |
Dataset loaders archive 2025-07-28
No loader listed in the archive.
Tasks archive 2025-07-28
License archive 2025-07-28
Modalities archive 2025-07-28
Languages archive 2025-07-28
Variants archive 2025-07-28
- TheoremQA
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