Update readme and compare runs in UI

Author: LYang-uva

README.md

@@ -105,14 +105,18 @@ Keys: [openrouter.ai/keys](https://openrouter.ai/keys). Never commit secrets.
 
 ## Quick start
 
-### One-off question
+### Web app
+```bash
+streamlit run src/miniBen/streamlit_app.py
+```
+This launches the MiniBen web interface in your browser, where you can configure your model, run benchmarks, and explore results interactively — no Python scripting required.
 
-```python
-from miniBen import AIModel
+### Command line (`example.py`)
 
-model = AIModel("openrouter/free")
-content, reasoning = model.ask("Say hello in one sentence.", reasoning=False)
-print(content)
+```bash
+python -m miniBen.example --list
+python -m miniBen.example --benchmark creativity --model openrouter/free
+python -m miniBen.example --benchmark "cognitive flexibility" --reasoning
 ```
 
 ### Full benchmark (5 API calls)
@@ -131,14 +135,6 @@ print(results["outputs"][0])  # per-call detail
 print(results["score"])       # aggregate benchmark score
 ```
 
-### Command line (`example.py`)
-
-```bash
-python -m miniBen.example --list
-python -m miniBen.example --benchmark creativity --model openrouter/free
-python -m miniBen.example --benchmark "cognitive flexibility" --reasoning
-```
-
 ---
 
 ## Benchmarks