| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| AndroidControl Task-Unseen | T3A* (Qwen2.5-7B-Instruct-ASL) | SSR62.3 | 20 | 11d ago | |
| AndroidControl (Cat-Unseen) | T3A* (Qwen2.5-7B-Instruct-ASL) | Step Success Rate (SSR)61.2 | 10 | 11d ago | |
| AndroidControl (IDD) | T3A* (Qwen2.5-7B-Instruct-ASL) | Step Success Rate (SSR)69.4 | 10 | 11d ago |