OpenClaw Arena Model Leaderboard — leaderboard
Personal AI agent benchmark evaluating frontier models across real-world OpenClaw-style tasks.
Metric: Avg Score (self-reported). Source: benchmarklist.com. Status: saturation imminent. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.5 | 67.4 |
| 2 | GPT-5.2 | 64.4 |
| 3 | Gemini 2.5 Pro | 63.8 |
| 4 | GPT-5.1 | 62.5 |
| 5 | Claude Sonnet 4.6 | 62.4 |
| 6 | Claude Opus 4.6 | 61.7 |
| 7 | Gemini 3.1 Pro (Preview) | 61 |
| 8 | GPT-5 Mini | 60.8 |
| 9 | GPT-4.1 | 60.5 |
| 10 | Claude Sonnet 4 | 57.8 |
| 11 | Claude Sonnet 4.5 | 57.5 |
| 12 | GPT-4o | 52.2 |
| 13 | GPT-4o Mini | 42.1 |
Interactive version: theaggregate.ai/benchmark?slug=openclaw-arena-model-leaderboard · How the rankings work · Data refreshed daily, snapshot 2026-07-22.