Benchmark
TheoremQA
A theorem-driven question answering dataset containing 800 high-quality questions covering 350+ theorems from Math, Physics, EE&CS, and Finance. Designed…
- Modality
- text
- Categories
- math, physics, reasoning, finance
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 6
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Qwen2 72B Instruct | Qwen | 0.444 | 2024-07-23 | evidence |
| Qwen2 7B Instruct | Qwen | 0.253 | 2024-07-23 | evidence |
| Qwen2.5 14B Instruct | Qwen | 0.43 | 2024-09-19 | evidence |
| Qwen2.5 32B Instruct | Qwen | 0.441 | 2024-09-19 | evidence |
| Qwen2.5-Coder 32B Instruct | Qwen | 0.431 | 2024-09-19 | evidence |
| Qwen2.5-Coder 7B Instruct | Qwen | 0.34 | 2024-09-19 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.