EnterpriseClawBench (Hermes) — leaderboard
Metric: Primary score (%). Source: frontisai.github.io. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 61.96 |
| 2 | DeepSeek V4 Pro | 58.55 |
| 3 | Kimi K2.6 | 56.13 |
| 4 | MiniMax-M3 | 52.46 |
| 5 | Claude Sonnet 4.6 | 45.75 |
| 6 | Claude Opus 4.6 | 42.54 |
| 7 | Claude Haiku 4.5 | 40.48 |
| 8 | GPT-4.1 Mini | 28.59 |
| 9 | Qwen 3 235B A22B | 27.03 |
Interactive version: theaggregate.ai/benchmark?slug=enterpriseclawbench-hermes · How the rankings work · Data refreshed daily, snapshot 2026-07-22.