EvalScope integration: one-command evaluation support for MiniWoB

[Yunnglin]

Hi ServiceNow/BrowserGym maintainers,

EvalScope now supports MiniWoB. 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 MiniWoB and want a quick path to evaluate a hosted or locally served model.
For MiniWoB, EvalScope runs the benchmark through BrowserGym and uses a native function-calling browser-action agent workflow.

Example:

evalscope eval \
  --model YOUR_MODEL \
  --api-url OPENAI_API_COMPAT_URL \
  --api-key EMPTY_TOKEN \
  --datasets miniwob \
  --limit 10

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

Some benchmarks may require additional assets, media files, browser/runtime dependencies, or judge-model configuration for a full run; the EvalScope guide above includes the benchmark-specific setup notes.

If this is useful for your community, we can follow up with a small README/Docs PR linking to the EvalScope usage guide.