# Local benchmark-score simulation only; this does not run the real benchmarks.
def evaluate(results):
    total = len(results)
    passed = sum(1 for _, ok in results if ok)
    print("Benchmark results:")
    for name, ok in results:
        print(f"{name}: {'PASS' if ok else 'FAIL'}")
    print(f"Pass rate: {passed}/{total} = {passed / total * 100:.1f}%")

print("=== Agent Evaluation Demo ===")
print("This is a sample evaluation, not an official AgentBench/SWE-bench run.")
results = [
    ("Tool-use task", True),
    ("Planning task", True),
    ("Repository bug fix", False),
    ("Test generation", True),
]
evaluate(results)
