BoxPwnr CTF Bench (claude_code): leaderboard
Metric: Mean published platform score (%); observed platforms only; claude_code. Source: github.com. Saturation forecast: Around March 2028. 3 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6 | 33.77 |
| 2 | Claude Sonnet 4.6 | 27.05 |
Interactive version: theaggregate.ai/benchmark?slug=boxpwnr-ctf-bench-claude-code · How It Works · Data refreshed daily, snapshot 2026-10-09.