Security research models, measured.

Curated detection-engineering, malware-analysis and threat-intel models.

All models

SearchSpecialtyAvailabilityTierSort

Capability

ReasoningVision

1 of 25

Threat detection & defense1

Llama-Primus-Reasoning

CTI reasoning

CVE/CWE · security reasoning · Q4_K_M

Trend Micro's reasoning model, continued-pretrained on the open Primus cybersecurity corpus over Llama-3.1-8B.

32K ctx

$0.15 in · $0.60 out

per Mtok · Available

not scored yet

Model catalog — measured, not marketed · AdversariaLLM