"""
L2-Bench response generation and LLM-as-judge scoring using inspect-ai.

Reference implementation of the pipeline described in
*L2-Bench: An Evaluation Benchmark for Measuring LLM Capabilities in Second
Language Education* (arXiv:2607.08842).

Version | Date       | Author    | Change comment
--------|------------|-----------|---------------
1.0.0   | 2026-07-29 | M. Ku     | Initial open-source release
"""

__version__ = "1.0.0"