Executable Games - Inter-Game Boundary Control: leaderboard
Metric: Success Rate (%; each game starts after another game's full interaction history). Source: arxiv.org. Saturation forecast: Around December 2026. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 77.47 |
| 2 | GPT-5.4 | 49.66 |
| 3 | DeepSeek V3.2 | 45.84 |
| 4 | Qwen 3 Max | 44.39 |
Interactive version: theaggregate.ai/benchmark?slug=executable-games-inter-game-boundary-control · How It Works · Data refreshed daily, snapshot 2026-09-25.