| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| StableToolBench (STB) | Llama3.1-8B | EM Accuracy49.25 | 16 | 4mo ago | |
| WebShop (WS) | Qwen2.5-7B | EM Accuracy79.05 | 16 | 4mo ago | |
| TextWorld (TW) | Qwen2.5-7B | EM Accuracy70.6 | 16 | 4mo ago | |
| SciWorld (SW) | Llama3.1-8B | EM Accuracy98.64 | 16 | 4mo ago | |
| ALFWorld (AW) | Qwen2.5-7B | EM Accuracy99.87 | 16 | 4mo ago | |
| LiDAR synthetic (NSP) | KE | RMSE22.4 | 10 | 1mo ago | |
| Atari Alien ALE (online) | Mind-Studio | Chosen-Action NSP Accuracy79 | 7 | 1mo ago | |
| Doppler radar tracking (Free) (test) | OKE | RMSE102.76 | 7 | 1mo ago | |
| Doppler radar tracking Const_a (test) | OKE | RMSE94.65 | 7 | 1mo ago | |
| Doppler radar tracking Const_v (test) | KE | RMSE85.4 | 7 | 1mo ago | |
| Doppler radar tracking Close (test) | KE | RMSE22.7 | 7 | 1mo ago | |
| Doppler radar tracking Toy (test) | OKE | RMSE86.93 | 7 | 1mo ago | |
| MOT20 | KE | RMSE0.4599 | 7 | 1mo ago | |
| LiDAR synthetic N=2000 trajectories (test) | KE | RMSE22.4 | 7 | 1mo ago | |
| Nine benchmark datasets (average) | T3R | R20.9492 | 6 | 25d ago |