ARMOR 2025: leaderboard
Metric: Accuracy (%) macro-averaged over the 12 doctrinal categories of ARMOR 2025 (519 three-option multiple-choice questions derived from the US Law of War, Rules of Engagement and Joint Ethics Regulation and verified by humans), zero-shot at API default parameters; an output that maps to no option or declines counts as a refusal; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 20 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o | 95.4 |
| 2 | GPT-4.1 Mini | 95 |
| 3 | DeepSeek V3 | 94.8 |
| 4 | O4 Mini | 94.8 |
| 5 | GPT-5 Mini | 94.3 |
| 6 | O3 Mini | 93.9 |
| 7 | Claude 3 Haiku | 93.3 |
| 8 | Claude Haiku 4.5 | 93.1 |
| 9 | DeepSeek R1 | 92.6 |
| 10 | Claude 3.5 Haiku | 92.1 |
| 11 | GPT-3.5 Turbo | 89.6 |
| 12 | Ministral 3 14B | 86.5 |
Interactive version: theaggregate.ai/benchmark?slug=armor-2025 · How It Works · Data refreshed daily, snapshot 2026-10-07.