evaluator = LongBenchEvaluator(
    model_path="path/to/model",
    num_gpus=N,
    output_file="path/to/results.json",
    eval_config={"batch_size": "auto"},
    vllm_config={"max_model_len": max_len}
)

results = evaluator.run()  # Returns LongBenchResult

{
  "en_multidoc": 0.5424139838230786,
  "zh_multidoc": 0.24335639081098673,
  "en_singledoc": 0.4233139199560039,
  "zh_singledoc": 0.46157875457875464,
  "en_summ": 0.27244809337990245,
  "zh_summ": 0.1359562304911904,
  "en_fewshot": 0.45692449627485754,
  "zh_fewshot": 0.24416666666666667,
  "en_synthetic": 0.3799285714285714,
  "zh_synthetic": 0.4775,
  "code_avg": 0.30225,
  "overall_score": 0.3581670097645466
}