EvalScope integration: one-command evaluation support for WideSearch

Hi ByteDance-Seed/WideSearch maintainers,

EvalScope now supports WideSearch. This gives users another way to run the benchmark when they want a standardized evaluation workflow around OpenAI-compatible model endpoints, saved predictions, scoring, and report generation.

This may be useful for users who find this repository while setting up WideSearch and want a quick path to evaluate a hosted or locally served model.

Example:

```bash
evalscope eval \
--model YOUR_MODEL \
--api-url OPENAI_API_COMPAT_URL \
--api-key EMPTY_TOKEN \
--datasets wide_search \
--limit 10
```

Docs: https://evalscope.readthedocs.io/en/latest/third_party/wide_search.html
EvalScope repo: https://github.com/modelscope/evalscope

We can also open a small PR adding this as a README/Docs note, linked to this issue.

Start by checking the repository README and documentation entry points for the best place to add an EvalScope note. Verify the linked WideSearch guide and the example command, then update the documentation so users can find the one-command evaluation workflow and understand what it provides.

Written by the indexing model from the issue text.