Run agent benchmark

from calibrate import Calibrate

client = Calibrate(
    api_key="your_api_key",
)

client.agent_tests.benchmark(
    agent_uuid="f47ac10b-58cc-4372-a567-0e02b2c3d479",
    models=[
        "openai/gpt-4.1",
        "anthropic/claude-sonnet-4"
    ],
)