feat: implement dataset-agnostic router benchmark

[rootfs]

What type of PR is this?

The router_reason_bench.py is based on MMLU-Pro. Need coverage of other datasets to fully eval the differences between the router vs direct vLLM calls.

What this PR does / why we need it:

Which issue(s) this PR fixes:

Fixes #

Release Notes: Yes/No

[netlify]

✅ Deploy Preview for vllm-semantic-router ready!

Name	Link
🔨 Latest commit	7849a2a
🔍 Latest deploy log	https://app.netlify.com/projects/vllm-semantic-router/deploys/68c4815158c5980008297aae
😎 Deploy Preview	https://deploy-preview-124--vllm-semantic-router.netlify.app
📱 Preview on mobile	Toggle QR Code... Use your smartphone camera to open QR code link.

---

To edit notification comments on pull requests, go to your Netlify project configuration.

[github-actions]

👥 vLLM Semantic Team Notification

The following members have been identified for the changed files in this PR and have been automatically assigned:

📁 bench

Owners: @yuezhu1, @Xunzhuo
Files changed:

• bench/README.md
• bench/benchmark_comparison.sh
• bench/dataset_factory.py
• bench/dataset_implementations/__init__.py
• bench/dataset_implementations/arc_dataset.py
• bench/dataset_implementations/commonsenseqa_dataset.py
• bench/dataset_implementations/gpqa_dataset.py
• bench/dataset_implementations/hellaswag_dataset.py
• bench/dataset_implementations/mmlu_dataset.py
• bench/dataset_implementations/truthfulqa_dataset.py
• bench/dataset_interface.py
• bench/router_reason_bench_multi_dataset.py
• bench/bench_plot.py
• bench/router_reason_bench.py

---

🎉 Thanks for your contributions!

This comment was automatically generated based on the OWNER files in the repository.