Horizon - OpenClaw (LCM) - Medium: leaderboard
Metric: Task Pass Rate (%). Source: www.orinlabs.ai. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | claude-opus-4.8 | 70.77 |
| 2 | gpt-5.5 | 61.54 |
| 3 | gemini-3.5-flash | 60 |
| 4 | gemini-3.1-pro-preview | 55.38 |
| 5 | deepseek-v4-pro | 43.08 |
| 6 | claude-sonnet-4.5 | 38.46 |
| 7 | claude-haiku-4.5 | 27.69 |
Interactive version: theaggregate.ai/benchmark?slug=horizon-openclaw-lcm-medium · How It Works · Data refreshed daily, snapshot 2026-10-09.