HIDBench - NodLink WIN10: 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 Windows 10 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 WIN10 host logs (2,411 events, 136 malicious); higher is better. Source: arxiv.org. Saturation forecast: Not forecast. 9 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1GPT-4.137.3#506
2Claude Opus 4.634.8#114
3Gemini 2.5 Flash34.1#466
4DeepSeek V3.230.5#425
5Claude Sonnet 4.525#267
6GPT-5.222.4#190
7Qwen 3.6 Plus21.8#245
8GPT-OSS-120B18.7#712
9Claude Sonnet 416.8#414

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=hidbench-nodlink-win10 · How It Works · Data refreshed daily, snapshot 2026-11-22.