TheoremQA
7 models
Top 5 Models Performance
| tiger-lab: general-reasoner-qwen3-4b | ######################################## | 48.3 |
| Qwen: qwen2.5-coder-32b | #################################### | 43.1 |
| Qwen: qwen2.5-coder-14b | ################################# | 39.6 |
| Qwen: qwen2.5-coder-7b | ############################ | 34 |
| Qwen: qwen2.5-coder-3b | ######################## | 29.5 |
| Rank | Model | Score | |
|---|---|---|---|
| ❓ | 1 | tiger-lab: general-reasoner-qwen3-4b | 48.3 |
| 🇨🇳 | 2 | Qwen: qwen2.5-coder-32b通义千问 | 43.1 |
| 🇨🇳 | 3 | Qwen: qwen2.5-coder-14b通义千问 | 39.6 |
| 🇨🇳 | 4 | Qwen: qwen2.5-coder-7b通义千问 | 34 |
| 🇨🇳 | 5 | Qwen: qwen2.5-coder-3b通义千问 | 29.5 |
| 🇨🇳 | 6 | Qwen: qwen2.5-coder-1.5b通义千问 | 21.4 |
| 🇨🇳 | 7 | Qwen: qwen2.5-coder-0.5b通义千问 | 14.3 |