phi-3-mini 3.8B
开源来自 Microsoft · 发布于 2024-01-01
61.0
平均分
N/A
输入价格
N/A
输出价格
N/A
上下文窗口
text
类型
Tested on 8 benchmarks with 61.0% average. Top scores: OpenBookQA (84.0%), ARC AI2 (79.9%), HellaSwag (68.9%).
基准测试分数
| 基准测试 | 类别 | 分数 | Bar |
|---|---|---|---|
| OpenBookQA | knowledge | 84.0 | |
| ARC AI2 | knowledge | 79.9 | |
| HellaSwag | knowledge | 68.9 | |
| TriviaQA | knowledge | 64.0 | |
| BBH | reasoning | 62.3 | |
| MMLU | knowledge | 58.4 | |
| Winogrande | knowledge | 41.6 | |
| ANLI | knowledge | 29.2 |
相似模型
OpenAI
61.2
Alibaba Qwen
60.7
Google DeepMind
60.6
Alibaba
60.6