Horizon - Hermes - Easy: leaderboard
Metric: Task Pass Rate (%). Source: www.orinlabs.ai. 3 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | gpt-5.5 | 72.31 |
| 2 | claude-opus-4.8 | 64.62 |
| 3 | claude-sonnet-4.5 | 52.31 |
Interactive version: theaggregate.ai/benchmark?slug=horizon-hermes-easy · How It Works · Data refreshed daily, snapshot 2026-10-09.