No traffic data available yet
Data is sourced from SimilarWeb
关于 APIEval-20
APIEval-20 is a black-box benchmark for API testing agents. Each agent gets only a JSON schema and one sample payload, then generates a test suite. We run those tests against live reference APIs with planted bugs and score bug detection, API coverage, and efficiency. Unlike LLM-as-judge evals, scoring is fully objective: a bug is either caught or it isn’t. Tasks span auth, errors, pagination, schemas, and multi-step flows. Open on Hugging Face.
常见问题
APIEval-20 是什么？
APIEval-20 是 APIEval-20 is a black-box benchmark for API testing agents. Each agent gets only a JSON schema and one sample payload, then generates a test suite. We run those tests against live reference APIs with planted bugs and score bug detection, API coverage, and efficiency. Unlike LLM-as-judge evals, scoring is fully objective: a bug is either caught or it isn’t. Tasks span auth, errors, pagination, schemas, and multi-step flows. Open on Hugging Face.
APIEval-20 免费吗？
是的，APIEval-20 免费使用。
APIEval-20 有哪些替代品？
APIEval-20 的热门替代品包括 Airtop Auth, OpenAI o3-mini, Anything API, Fish Audio S1。可在上方比较它们的月流量和功能。
