AI benchmarks and leaderboards are different things
Learn the difference between a benchmark, an evaluation run and a leaderboard, and use each to answer the right question.
LLM Stats
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.
Evaluation context and evidence
- Source
- LLM Stats
- Publisher
- Not recorded
- Benchmark release
- Not recorded
- Collected
- 2026-08-17
- Modality
- text
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Original sources
Reported results 6
Shown in source observation order, not ranked. Dates retain the precision provided by the source.
| Model | Value | Unit | Protocol | Reported date and basis | Source |
|---|---|---|---|---|---|
| Qwen2 72B Instruct | 0.444 | Not recorded | Not recorded | 2024-07-23 · model_announcement | LLM Stats |
| Qwen2.5 32B Instruct | 0.441 | Not recorded | Not recorded | 2024-09-19 · model_announcement | LLM Stats |
| Qwen2.5-Coder 32B Instruct | 0.431 | Not recorded | Not recorded | 2024-09-19 · model_announcement | LLM Stats |
| Qwen2.5 14B Instruct | 0.43 | Not recorded | Not recorded | 2024-09-19 · model_announcement | LLM Stats |
| Qwen2.5-Coder 7B Instruct | 0.34 | Not recorded | Not recorded | 2024-09-19 · model_announcement | LLM Stats |
| Qwen2 7B Instruct | 0.253 | Not recorded | Not recorded | 2024-07-23 · model_announcement | LLM Stats |