Faibench Frontier InfraBench
Description
Phi-Bench (Φ-Bench): 85 open-source LLM-infrastructure engineering tasks for frontier LLMs & coding agents (KFC/LH/E2E). Self-contained public Dockerfile + offline scoring + reference solution per task. Website: llminfrabench.com
Installation
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open the source below and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
README
Φ-Bench: Can Large Language Models Engineer the Infrastructure That Powers Them?
*The **Frontier AI Infrastructure Benchmark** for evaluating frontier LLMs and autonomous coding agents on real-world **ML systems and LLM infrastructure engineering** — also written **FAI-Bench** / **ΦBench**.*
**85 open-source LLM-infrastructure engineering tasks** — build a public Docker image, solve the task offline, and score against a grader shipped with the package.
🔗 [faibench.org](https://faibench.org/)
[](LICENSE)  [](https://faibench.org/) [](https://huggingface.co/datasets/faibench-Frontier-Infra-Bench/faibench_Frontier_Infra_Bench) 
🌐 **English** · [简体中文](README.zh-CN.md)
Contents
- Can LLMs Engineer the Infrastructure That Powers Them?
- Benchmark Overview
- Directory shape
- Running a Task
- Using the Task Runner
- Important Conventions
- Reproducibility
- Package Verification
- License
Can LLMs Engineer the Infrastructure That Powers Them?
**Can LLMs Engineer the Infrastructure That Powers Them? To answer this question, we introduce Φ-Bench—the most comprehensive and realistic benchmark for LLM infrastructure engineering.**
✅ **Broadest coverage.** ✅ **Real-world engineering.** ✅ **Frontier-level difficulty.**
To bu
Related Skills
Docker
---
Kubernetes
---
AWS Skills
AWS development with CDK best practices, cost optimization MCP servers, and serverless/event-driven architectu
Composio Split
Manage Split feature flags and experiments
**claude-code-router**
(25.3k ⭐) - Use Claude Code as the foundation for coding infrastructure, allowing you to decide how to interac
CLAUDE.md CI/CD Wiki
Community patterns for CLAUDE.md configuration in CI/CD pipelines.
