Add "first impression" benchmark to bench.sh

### Is your feature request related to a problem or challenge?

Many people who use DataFusion for the first time are querying a single CSV file, so we may want to benchmark that scenario (via bench.sh -- see https://github.com/apache/arrow-datafusion/pull/6131)

### Describe the solution you'd like

I would like to add a "first impression" performance benchmark -- perhaps based on querying some subset of the ClickBench #6128 in CSV format

### Describe alternatives you've considered

_No response_

### Additional context

Suggested by @andygrove here https://github.com/apache/arrow-datafusion/issues/6127#issuecomment-1523680537

Start with bench.sh and review the related DataFusion pull request 6131 and ClickBench issue 6128 for the existing benchmark conventions. Define a representative subset of the ClickBench data in CSV format, add the first-impression scenario, and verify that bench.sh runs it and reports performance.

Written by the indexing model from the issue text.