TACTL — leaderboard

Offensive cybersecurity knowledge test evaluating LLMs on tactical cyber operations, threat intelligence, and adversarial techniques.

Metric: Accuracy (%). Source: huggingface.co. Status: saturated. 8 models tracked.

Top models

#ModelScore
1DeepSeek R195.9
2DeepSeek V393.15
3Llama 3.1 405B90.9
4GPT-4o89.25
5Qwen 2.5 72B Instruct88.75
6Llama 3.3 70B79.35
7Mixtral 8x22B62.5

Interactive version: theaggregate.ai/benchmark?slug=tactl · How the rankings work · Data refreshed daily, snapshot 2026-07-22.