HIDBench - NodLink HW17: 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 NodLink simulated HW17 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 NodLink simulated-data HW17 host logs (481 events, 16 malicious); higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 9 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1GPT-5.266.5#185
2GPT-4.162.2#505
3Gemini 2.5 Flash57.3#463
4Claude Opus 4.654.2#113
5Qwen 3.6 Plus46.2#238
6Claude Sonnet 4.537.9#261
7Claude Sonnet 436.5#410
8DeepSeek V3.230#419
9GPT-OSS-120B21.7#704

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

Interactive version: theaggregate.ai/benchmark?slug=hidbench-nodlink-hw17 · How It Works · Data refreshed daily, snapshot 2026-11-21.