feat(evaluation): add LeaBench computer-use scorer

This commit is contained in:
Dom
2026-05-24 21:21:17 +02:00
parent 345762330b
commit ea1f57afb1
5 changed files with 495 additions and 0 deletions

15
tools/lea_bench.py Normal file
View File

@@ -0,0 +1,15 @@
#!/usr/bin/env python3
"""CLI wrapper for the LéaBench computer-use evaluator."""
import sys
from pathlib import Path
ROOT = Path(__file__).resolve().parents[1]
if str(ROOT) not in sys.path:
sys.path.insert(0, str(ROOT))
from core.evaluation.computer_use_bench import main
if __name__ == "__main__":
raise SystemExit(main())