OrgForge-IT: leaderboard
Synthetic insider-threat detection benchmark built from OrgForge organizational simulation telemetry with triage, verdict, and false-positive scoring.
Metric: Verdict F1 (self-reported). Source: benchmarklist.com. Status: saturation imminent. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6 | 100 |
| 2 | Claude Sonnet 4.6 | 80 |
| 3 | Llama 4 Maverick | 80 |
| 4 | Claude Haiku 4.5 | 80 |
| 5 | DeepSeek V3.2 | 80 |
| 6 | GLM-5 | 80 |
| 7 | Llama 3.3 70B | 80 |
| 8 | Qwen3 Coder | 80 |
Interactive version: theaggregate.ai/benchmark?slug=orgforge-it · How It Works · Data refreshed daily, snapshot 2026-09-05.