EnterpriseClawBench (Claude Code): leaderboard
FrontisAI's EnterpriseClawBench — enterprise software-engineering agent tasks run with the Claude Code agent scaffold; primary resolved score (%) over a small frontier pool.
Metric: Primary score (%). Source: frontisai.github.io. Saturation forecast: Around January 2027. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.6 | 64.41 | #90 |
| 2 | Claude Opus 4.6 | 63.51 | #63 |
| 3 | Claude Haiku 4.5 | 51.33 | #280 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=enterpriseclawbench-claude-code · How It Works · Data refreshed daily, snapshot 2026-10-20.