SkillSafetyBench - Task Success: leaderboard
Metric: Task success (%; mean reward of the original SkillsBench task over the 155 attacked cases, scored by the task's own tests, 1.0 for a fully completed task; each row is a CLI agent harness with a model backend). Source: arxiv.org. Saturation forecast: Around August 2027. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 (Codex) | 42.6 |
| 2 | Claude Opus 4.6 (Claude Code) | 40 |
| 3 | GPT-5.4 (Codex) | 38.7 |
Interactive version: theaggregate.ai/benchmark?slug=skillsafetybench-task-success · How It Works · Data refreshed daily, snapshot 2026-09-26.