AeroCopilotBench - Tier-2 Safety-Gated Outcome: leaderboard
Metric: Goal attainment (%; zero on any safety violation). Source: arxiv.org. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 Sol (High) | 91.1 |
| 2 | Gemini 3.5 Flash (High) | 84.4 |
| 3 | GLM-5.1 (Thinking) | 83.1 |
| 4 | GLM-5.2 (High) | 78.4 |
| 5 | DeepSeek V4 Pro (High) | 76.6 |
| 6 | DeepSeek V4 Flash (High) | 67.7 |
| 7 | Kimi K2.6 (Thinking) | 67.5 |
| 8 | Qwen 3.5 397B A17B (Thinking) | 54.7 |
| 9 | MiniMax-M2.5 | 47.5 |
| 10 | Nex N2 Pro | 45.9 |
| 11 | Qwen 3.5 122B A10B (Thinking) | 45.8 |
Interactive version: theaggregate.ai/benchmark?slug=aerocopilotbench-tier-2-safety-gated-outcome · How It Works · Data refreshed daily, snapshot 2026-09-19.