← Back to directory

agent-bench

Benchmark harness for comparing AI coding agents (inber, Claude Code, OpenClaw) on identical tasks

Setup / get started

Start from the GitHub repository: source code and README for agent-bench.

Alternatives to agent-bench

Similar projects in this directory:

  • claw-bench — Measure AI agents’ performance with standardized tests across 314 tasks, 33 domains, and 4 difficulty levels for…
  • creedflow — AI-powered project orchestration platform. Describe a project in natural language — CreedFlow analyzes it, creates…
  • laborany — LaborAny 的初衷,是把强大的 AI Agent 能力从“少数人的命令行工具”变成“每个人都能用的桌面生产力”。它基于 Claude Code CLI…
  • ResearchClawBench — ResearchClawBench: Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery
  • OpenClaw — An open-source task orchestration platform for [OpenCode](https://opencode.ai) and…
By kayushkinAdded 3/8/2026