Code Block
import { Bench } from "benchthing";
const bench = new Bench("super-glue");
await bench.run({
benchmark: "super-glue",
taskId: "1",
models: yourLanguageModels
});
const result = await bench.getResult("1");
from benchthing import Bench
bench = Bench("webarena")
bench.run(
benchmark="webarena",
task_id="1",
agents=your_agents
)
result = bench.get_result("1")