HIDBench - DARPA E5 THEIA: leaderboard

HIDBench (2026) tests LLMs as host-based intrusion detectors: the model reads windows of serialized provenance-graph events from system logs and must flag the malicious ones, here on the DARPA Engagement 5 THEIA host logs. Matthews correlation coefficient of malicious-event detection times 100 (-100 to 100); higher is better.

Metric: Matthews correlation coefficient of malicious-event detection times 100 (-100 to 100), from the HIDBench pipeline (attack-centric windows of host provenance-graph events serialized for the LLM, high-confidence evidence identification, k-hop context expansion, then attack narrative and indicator-of-compromise output) on the DARPA Engagement 5 THEIA host logs (112,741 events, 56 malicious); higher is better. Source: arxiv.org. Saturation forecast: Around June 2028. 9 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Claude Opus 4.612.2#113
2GPT-5.27.4#185
3GPT-OSS-120B6.6#704
4Claude Sonnet 46.6#410
5Claude Sonnet 4.55.4#261
6Gemini 2.5 Flash2.4#463
7GPT-4.11.9#505
8DeepSeek V3.21.9#419
9Qwen 3.6 Plus1.7#238

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=hidbench-darpa-e5-theia · How It Works · Data refreshed daily, snapshot 2026-11-21.