SecIT Bench (Claude Code): leaderboard
The SecIT Bench scenario set run inside the Claude Code agent product rather than a plain model harness. Scored identically to the Pydantic AI board, and kept separate because the scaffold is part of what is being measured: the same model moves by up to three points between harnesses.
Metric: Accuracy (%). Source: cribl.io. Saturation forecast: Around March 2027. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5 | 78.64 | #12 |
| 2 | Claude Sonnet 5.5 | 69.93 | #11 |
| 3 | Claude Opus 4.8 | 67.14 | #37 |
| 4 | Claude Sonnet 5 | 65.93 | #57 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=secit-bench-claude-code · How It Works · Data refreshed daily, snapshot 2026-10-20.