AgencyBench

Long-horizon agent benchmark: 32 scenarios, 138 tasks, ~1M tokens and ~90 tool calls; Docker sandbox and rubric-based + LLM judges.

evalssandboxpython

Stars: 105
Adoption surface: complex
Autonomy: headless
Recovery: none
License: ✅ open-source
Category: Evaluation and benchmarking harnesses

Repository ↗ Example: AgencyBench leaderboard ↗

Related in Evaluation and benchmarking harnesses

Agent Lightning
SWE-bench
AgentBench
inspect_ai
WebArena
ClawBench

Maintain AgencyBench? Add the badge

Paste this into your README so readers can find the list and see how AgencyBench compares:

[![Best of Agent Harnesses](https://img.shields.io/badge/%F0%9F%8F%86_Best_of-Agent_Harnesses-5ac4bf)](https://github.com/RyanAlberts/best-of-Agent-Harnesses)