EnterpriseClawBench (DeepAgents) — leaderboard
Metric: Primary score (%). Source: frontisai.github.io. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.6 | 63.18 |
| 2 | GPT-5.5 | 62.89 |
| 3 | Claude Opus 4.6 | 57.27 |
| 4 | DeepSeek V4 Pro | 56.21 |
| 5 | MiniMax-M3 | 51.96 |
| 6 | Kimi K2.6 | 51.49 |
| 7 | Claude Haiku 4.5 | 50.67 |
| 8 | GPT-4.1 Mini | 26 |
| 9 | Qwen 3 235B A22B | 24.13 |
Interactive version: theaggregate.ai/benchmark?slug=enterpriseclawbench-deepagents · How the rankings work · Data refreshed daily, snapshot 2026-07-22.