CyberMetric — leaderboard
Multiple-choice cybersecurity knowledge Q&A across 500 questions covering threats, vulnerabilities, defenses, and best practices. Tests breadth of security knowledge.
Metric: Accuracy (%). Source: huggingface.co. Status: saturated. 25 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o | 92.45 |
| 2 | GPT-4 Turbo | 92.26 |
| 3 | Mixtral 8x7B Instruct | 90.6 |
| 4 | Gemini 1.0 Pro | 86.64 |
| 5 | GPT-3.5 Turbo | 86.42 |
| 6 | Mistral 7B Instruct (v0.2) | 77.09 |
| 7 | Llama 3 8B Instruct | 75.61 |
| 8 | zephyr-7B-beta | 73.71 |
| 9 | flan-t5-xxl | 72.38 |
| 10 | Llama 2 70B | 71.53 |
| 11 | Qwen 1.5 7B | 63.87 |
| 12 | Qwen1.5-MoE-A2.7B | 62.37 |
| 13 | Qwen-7B | 52.9 |
| 14 | Phi-2 | 51.7 |
| 15 | Llama3-ChatQA-1.5-8B | 51.41 |
Interactive version: theaggregate.ai/benchmark?slug=cybermetric · How the rankings work · Data refreshed daily, snapshot 2026-07-22.