# Chart Analysis: Accuracy Comparison by Max Cluster Size
## Chart Type
Bar chart comparing accuracy percentages between two methods: **Coding** (blue) and **MC** (pink).
## Axes
- **X-axis**: "Max cluster size" with categories:
`None`, `32`, `16`, `8`, `4`, `2`
- **Y-axis**: "Accuracy (%)" ranging from 0.0 to 0.45.
## Legend
- **Blue**: Coding
- **Pink**: MC
## Data Points
| Max Cluster Size | Coding Accuracy (%) | MC Accuracy (%) |
|-------------------|---------------------|-----------------|
| None | ~0.41 | ~0.45 |
| 32 | ~0.12 | ~0.45 |
| 16 | ~0.11 | ~0.45 |
| 8 | ~0.11 | ~0.45 |
| 4 | ~0.21 | ~0.45 |
| 2 | — | ~0.36 |
## Key Trends
1. **MC consistently outperforms Coding** across all max cluster sizes, with accuracy remaining near 0.45% for most categories.
2. **Coding accuracy varies significantly**:
- Highest at `None` (~0.41%).
- Lowest at `32`, `16`, and `8` (~0.11%).
- Slight improvement at `4` (~0.21%).
3. **MC accuracy drops sharply** at `2` (~0.36%), the only category where Coding data is absent.
## Observations
- No embedded text or additional annotations in the chart.
- Data suggests MC is more robust to cluster size variations, while Coding performance degrades with larger clusters.
