data/eval_report.md

# CodeWraith Model Evaluation Report

## Summary

| Metric | CodeWraith-8b (Llama-3.1-8B-Instruct) |
|--------|-----|
| Avg Structural Score | 0.95 |
| Function Coverage | 0.92 |
| Class Coverage | 0.81 |
| Argument Coverage | 1.00 |
| Return Type Coverage | 0.89 |
| Good Scores (>=80%) | 26 |
| Avg Inference Time (s) | 20.79 |

## CodeWraith-8b (Llama-3.1-8B-Instruct)

- Examples evaluated: 30
- Valid (parseable): 29
- Perfect scores: 17
- Total inference time: 623.6s