TheoremQA
A theorem-driven question answering dataset containing 800 high-quality questions covering 350+ theorems from Math, Physics, EE&CS, and Finance. Designed to evaluate AI models' capabilities to apply theorems to solve challenging university-level science problems.
Qwen2 72B Instruct from Alibaba Cloud / Qwen Team currently leads the TheoremQA leaderboard with a score of 0.444 across 6 evaluated AI models.
What TheoremQA measures
TheoremQA is a text benchmark that evaluates large language models on math, physics, reasoning, and finance tasks. LLM Stats tracks 6 models on this benchmark, with a maximum possible score of 1. Current average across reported models is 0.4, with the leader reaching 0.4.
Compare leaders on the best AI for math, best AI for physics, best AI for reasoning and best AI for finance leaderboards.
Publication
- Paper
- TheoremQA: A Theorem-driven Question Answering dataset
- Authors
- Wenhu Chen, Ming Yin, Max Ku, Pan Lu, and 5 others
- Published
- arXiv
- 2305.12524
Abstract
The recent LLMs like GPT-4 and PaLM-2 have made tremendous progress in solving fundamental math problems like GSM8K by achieving over 90% accuracy. However, their capabilities to solve more challenging math problems which require domain-specific knowledge (i.e. theorem) have yet to be investigated. In this paper, we introduce TheoremQA, the first theorem-driven question-answering dataset designed to evaluate AI models' capabilities to apply theorems to solve challenging science problems. TheoremQA is curated by domain experts containing 800 high-quality questions covering 350 theorems (e.g. Taylor's theorem, Lagrange's theorem, Huffman coding, Quantum Theorem, Elasticity Theorem, etc) from Math, Physics, EE&CS, and Finance. We evaluate a wide spectrum of 16 large language and code models with different prompting strategies like Chain-of-Thoughts and Program-of-Thoughts. We found that GPT-4's capabilities to solve these problems are unparalleled, achieving an accuracy of 51% with Program-of-Thoughts Prompting. All the existing open-sourced models are below 15%, barely surpassing the random-guess baseline. Given the diversity and broad coverage of TheoremQA, we believe it can be used as a better benchmark to evaluate LLMs' capabilities to solve challenging science problems. The data and code are released in https://github.com/wenhuchen/TheoremQA.
Qwen2 72B Instruct leads with 44.4%, followed by Qwen2.5 32B Instruct at 44.1% and Qwen2.5-Coder 32B Instruct at 43.1%.
Progress Over Time
Interactive timeline showing model performance evolution on TheoremQA
TheoremQA Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Alibaba Cloud / Qwen Team | 72B | — | — | ||
| 2 | Alibaba Cloud / Qwen Team | 33B | — | — | ||
| 3 | Alibaba Cloud / Qwen Team | 32B | — | — | ||
| 4 | Alibaba Cloud / Qwen Team | 15B | — | — | ||
| 5 | Alibaba Cloud / Qwen Team | 7B | — | — | ||
| 6 | Alibaba Cloud / Qwen Team | 8B | — | — |
FAQ
Common questions about TheoremQA.
More evaluations to explore
Related benchmarks in the same category
A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.
A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks. Features over 12,000 curated questions across 14 domains and causes a 16-33% accuracy drop compared to original MMLU.
All 30 problems from the 2025 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.
Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains
A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.
Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions