For Your Eyes Only - Constrained: leaderboard
Metric: Double-Pass Success Rate (%). Source: arxiv.org. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 96.33 |
| 2 | Gemini 3 Flash | 65 |
| 3 | GPT-OSS-120B | 53.67 |
| 4 | Qwen 3.6 Plus | 39 |
| 5 | DeepSeek V4 Flash | 39 |
| 6 | DeepSeek V4 Pro | 24 |
| 7 | Qwen 3.6 35B A3B | 8.67 |
Interactive version: theaggregate.ai/benchmark?slug=for-your-eyes-only-constrained · How It Works · Data refreshed daily, snapshot 2026-09-20.