agent-eval-bench
轻量级 Agent 评测台：任务集 + k 次采样 + Pass@k/Pass^k 双口径可靠性指标 + 判分器校准与失败归因。零依赖，clone 即跑。
What is agent-eval-bench?
轻量级 Agent 评测台：任务集 + k 次采样 + Pass@k/Pass^k 双口径可靠性指标 + 判分器校准与失败归因。零依赖，clone 即跑。
Maintain this project? Show that it is featured on YunoDB.
Markdown
[](https://yunodb.com/tools/serewballagent-eval-bench?utm_source=github&utm_medium=badge)HTML
<a href="https://yunodb.com/tools/serewballagent-eval-bench?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/serewballagent-eval-bench.svg" alt="Featured on YunoDB" height="20"></a>Keep exploring
View all alternatives Related tools
100/100
wechat-bot
🤖 Multi-platform IM AI Agent for Telegram, WhatsApp, Lark, and WeChat. Connects ChatGPT / Claude / Kimi / DeepSeek / Ollama / Pi for auto-replies, community an
100/100
pyod
A Python library for anomaly detection across tabular, time series, graph, text, image, and audio data. 60+ detectors, benchmark-backed ADEngine orchestration,
100/100
Open-Generative-AI
Unrestricted Open-source alternative to AI video platforms — Free AI image & video generation studio with 600+ models (Flux, Midjourney, Kling, Sora, Veo). No c