加载中...
加载中...
一个包含 7787 个多项选择题的基准，用于评估模型的常识推理能力。
Source: DataLearnerAI
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
| 排名 | 模型 | |||
|---|---|---|---|---|
| 1 | Gemma 2 - 9Bdefault | 68.2 | 2024-06-27 | 90 |
| 2 | Qwen2.5-7Bdefault | 63.7 | 2024-09-18 | 70 |
| 3 | Mistral-7B-Instruct-v0.3default | 60 | 2024-05-22 | 70 |
| 4 | Llama3.1-8Bdefault | 59.3 | 2024-07-23 | 80 |