> ## Documentation Index
> Fetch the complete documentation index at: https://docs.factory.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Agent Arena

> Agent Arena results and methodology for AI coding agents.

export const EloChart = ({data, valueKey = "elo", labelKey = "name", baseline = 1200}) => {
  const values = data.map(d => d[valueKey]);
  const maxDelta = Math.max(...values.map(v => Math.abs(v - baseline)));
  return <div className="space-y-3 my-6 not-prose">
      {data.map((item, idx) => {
    const value = item[valueKey];
    const delta = value - baseline;
    const barWidth = Math.abs(delta) / maxDelta * 40;
    const isAbove = delta >= 0;
    const isDroid = item[labelKey].toLowerCase().includes('droid') || item[labelKey].toLowerCase().includes('factory');
    return <div key={idx}>
            <div className="flex items-center gap-2 mb-1.5">
              <span className="w-6 text-sm font-mono text-zinc-400 dark:text-zinc-500 text-right">
                {idx + 1}
              </span>
              <span className="text-sm font-medium text-zinc-900 dark:text-zinc-100">
                {item[labelKey]}
              </span>
            </div>
            <div className="flex items-center gap-3">
              <div className="w-6" />
              <div className="flex-1 h-7 relative flex items-center">
                <div className="absolute left-1/2 top-0 bottom-0 w-px border-l border-dashed border-zinc-400 dark:border-zinc-500" />
                <div className="absolute top-0 bottom-0 rounded-sm transition-all duration-500" style={{
      width: `${barWidth}%`,
      left: isAbove ? '50%' : `${50 - barWidth}%`,
      background: isDroid ? 'linear-gradient(to right, #f97316, #fb923c)' : isAbove ? 'linear-gradient(to right, #a1a1aa, #d4d4d8)' : 'linear-gradient(to right, #d4d4d8, #a1a1aa)'
    }} />
                <span className="absolute text-xs font-mono text-zinc-600 dark:text-zinc-400" style={{
      left: isAbove ? `${50 + barWidth + 1}%` : `${50 - barWidth - 1}%`,
      transform: isAbove ? 'none' : 'translateX(-100%)'
    }}>
                  {value}
                </span>
              </div>
            </div>
          </div>;
  })}
      <div className="flex items-center gap-3 mt-1">
        <div className="w-6" />
        <div className="flex-1 relative h-4">
          <div className="absolute left-1/2 -translate-x-1/2 text-xs font-mono text-zinc-400 dark:text-zinc-500">
            {baseline}
          </div>
        </div>
      </div>
    </div>;
};

export const agentArenaData = [{
  name: "Factory Droid",
  elo: 1330
}, {
  name: "OpenAI Codex",
  elo: 1301
}, {
  name: "Devin",
  elo: 1263
}, {
  name: "Claude Code",
  elo: 1242
}, {
  name: "Cursor",
  elo: 1120
}, {
  name: "Gemini CLI",
  elo: 937
}];

Crowdsourced benchmark from [Design Arena](https://designarena.ai) where AI agents compete to accomplish complex tasks and solve real-world problems autonomously. Rankings are determined by Elo ratings derived from head-to-head comparisons voted on by real users.

### ELO Ratings

<EloChart data={agentArenaData} baseline={1200} />

*Last updated: December 2025*

### Methodology

1. **Task Assignment** - Both agents receive identical complex task specifications
2. **Autonomous Execution** - Each agent works independently to complete the task
3. **Side-by-Side Comparison** - Outputs are presented to human voters
4. **Elo Scoring** - Results contribute to Bradley-Terry Elo ratings

| Dimension             | Description                                       |
| --------------------- | ------------------------------------------------- |
| **Task Completion**   | Successfully accomplishing the assigned objective |
| **Quality of Output** | Accuracy and polish of the final result           |
| **Efficiency**        | Resource usage and execution speed                |
| **Robustness**        | Handling edge cases and unexpected situations     |

<Card title="Agent Arena Leaderboard" icon="trophy" href="https://www.designarena.ai/leaderboard/agents">
  View live rankings and vote on agent comparisons
</Card>