LLM Stats (TheoremQA): leaderboard
800 theorem-application questions spanning math, physics, EE, CS, and finance requiring application of scientific theorems to solve problems.
Metric: Score (%). Source: llm-stats.com. Saturation forecast: Estimated already saturated. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 2 72B Instruct | 44.4 | #576 |
| 2 | Qwen 2.5 32B Instruct | 44.1 | #498 |
| 3 | Qwen 2.5 Coder 32B Instruct | 43.1 | #528 |
| 4 | Qwen 2.5 14B Instruct | 43 | #647 |
| 5 | Qwen 2.5 Coder 7B Instruct | 34 | #951 |
| 6 | Qwen 2 7B Instruct | 25.3 | #991 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=llm-stats-theoremqa · How It Works · Data refreshed daily, snapshot 2026-10-20.