Last updated 26 days ago
pip install benchflow
uv add benchflow
from benchflow import load_benchmark bench = load_benchmark(benchmark_name="webarena", bf_token="your_benchflow_key") your_agents = youragent() job_ids = bench.run( agents=your_agents, api={"provider": "openai", "model": "gpt-4o-mini", "OPENAI_API_KEY": os.getenv("OPENAI_API_KEY")}, requirements_txt="webarena_requirements.txt", params={} ) results = bench.get_results(job_ids)
python test.py