OrgForge-IT: leaderboard
Synthetic insider-threat detection benchmark built from OrgForge organizational simulation telemetry with triage, verdict, and false-positive scoring.
Metric: Verdict F1 (imported). Source: arxiv.org. Source: benchmarklist.com. Saturation forecast: Around June 2027. 10 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.6 | 100 | #63 |
| 2 | Claude Sonnet 4.6 | 80 | #90 |
| 3 | Claude Haiku 4.5 | 80 | #280 |
| 4 | DeepSeek V3.2 | 80 | #205 |
| 5 | Llama 4 Maverick | 80 | #464 |
| 6 | GLM-5 | 80 | #141 |
| 7 | Llama 3.3 70B | 80 | #579 |
| 8 | Qwen3 Coder Next | 80 | #326 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=orgforge-it · How It Works · Data refreshed daily, snapshot 2026-10-20.