SecCodePLT — leaderboard
Evaluates LLMs on secure code generation and cyberattack helpfulness across 13 subtasks covering insecure coding patterns, reconnaissance, weaponization, and discovery.
Metric: Score (%). Source: huggingface.co. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | CodeLlama-34B-Instruct | 67.88 |
| 2 | Mixtral 8x22B | 58 |
| 3 | Claude 3.5 Sonnet | 54.4 |
| 4 | Llama 3.1 70B | 44.75 |
| 5 | GPT-4o | 44.15 |
Interactive version: theaggregate.ai/benchmark?slug=seccodeplt · How the rankings work · Data refreshed daily, snapshot 2026-07-22.