Lyptus Cyber Time Horizons - NL2Bash: leaderboard
Lyptus Research offensive cyber time-horizon run of NL2Bash, measuring command-generation success at a 2M token budget.
Metric: pass@1 at 2M tokens (%). Source: lyptusresearch.org. Saturation forecast: Estimated already saturated. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 | 100 | #31 |
| 2 | GPT-5.3 Codex | 100 | #69 |
| 3 | Claude Opus 4.6 | 88.9 | #63 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=lyptus-cyber-time-horizons-nl2bash · How It Works · Data refreshed daily, snapshot 2026-10-20.