kth8/Qwen3.5-4B-GPQA-Diamond-benchmark
收藏Hugging Face2026-04-09 更新2026-04-12 收录
下载链接：
https://hf-mirror.com/datasets/kth8/Qwen3.5-4B-GPQA-Diamond-benchmark
下载链接
链接失效反馈官方服务：
资源简介：
---
license: apache-2.0
language:
- en
base_model: Qwen/Qwen3.5-4B
datasets:
- fingertap/GPQA-Diamond
---
Benchmark of [Qwen/Qwen3.5-4B](https://huggingface.co/Qwen/Qwen3.5-4B) against [fingertap/GPQA-Diamond](https://huggingface.co/datasets/fingertap/GPQA-Diamond) dataset.
Accuracy: 72.7% with Python tool.
| Metric | Value |
|----------------------|---------------|
| **Correct** | 144 |
| **Incorrect** | 54 |
| **Errors** | 0 |
| **Total samples** | 198 |
| **Python tool calls**| 324 |
| **Total completion tokens** | 927,833 |
Raw stats:
```json
{
"accuracy": 0.727,
"correct": 144,
"incorrect": 54,
"error": 0,
"total": 198,
"python_tool_calls": 324,
"completion_tokens": 927833
}
```
提供机构：
kth8
