HIDBench - DARPA E3 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 3 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 3 THEIA host logs (121,263 events, 64 malicious); higher is better. Source: arxiv.org. Saturation forecast: Around September 2027. 9 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.6 | 28.3 | #113 |
| 2 | GPT-5.2 | 25.5 | #185 |
| 3 | Claude Sonnet 4.5 | 25 | #261 |
| 4 | GPT-4.1 | 25 | #505 |
| 5 | Claude Sonnet 4 | 22.4 | #410 |
| 6 | DeepSeek V3.2 | 22.1 | #419 |
| 7 | GPT-OSS-120B | 21.6 | #704 |
| 8 | Qwen 3.6 Plus | 18.7 | #238 |
| 9 | Gemini 2.5 Flash | 17.7 | #463 |
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-e3-theia · How It Works · Data refreshed daily, snapshot 2026-11-21.