kth8/gpt-oss-20b-GPQA-Diamond-benchmark
收藏Hugging Face2026-04-10 更新2026-04-12 收录
下载链接：
https://hf-mirror.com/datasets/kth8/gpt-oss-20b-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: openai/gpt-oss-20b
datasets:
- fingertap/GPQA-Diamond
---
Benchmark of [openai/gpt-oss-20b](https://huggingface.co/openai/gpt-oss-20b) against [fingertap/GPQA-Diamond](https://huggingface.co/datasets/fingertap/GPQA-Diamond) dataset.
Accuracy: 69.6% with Python tool.
| Metric | Value |
|----------------------|---------------|
| **Correct** | 138 |
| **Incorrect** | 60 |
| **Errors** | 0 |
| **Total samples** | 198 |
| **Python tool calls**| 112 |
| **Total completion tokens** | 826,954 |
Raw stats:
```json
{
"accuracy": 0.697,
"correct": 138,
"incorrect": 60,
"error": 0,
"total": 198,
"python_tool_calls": 112,
"completion_tokens": 826954
}
```
提供机构：
kth8
