| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Sudoku | ESPO | Accuracy92.7 | 141 | 1mo ago | |
| Rover(r, w, s, o) domain (test) | GPA + Soft-FLARES | Planning Time0.01 | 104 | 4mo ago | |
| Countdown | BGPO | Accuracy87.5 | 101 | 1mo ago | |
| IPC Domains | Flexibility93 | 99 | 3mo ago | ||
| nuScenes (val) | GuideFlow | Collision Rate (Avg)0.07 | 97 | 2mo ago | |
| NAVSIM (navtest) | DiffusionDrive | NC99.6 | 78 | 1mo ago | |
| NAVSIM (test) | DriveSuprim | PDMS93.5 | 75 | 26d ago | |
| Rotating DDI | GSS | Mean Undiscounted Return48.194 | 66 | 18d ago | |
| NAVSIM v1 (test) | Human driver | PDMS94.8 | 62 | 1mo ago | |
| Room Domain | Our Proposed Framework | Time (s)0.15 | 56 | 4mo ago | |
| Traffic Norms Domain | T (s)0.592 | 52 | 4mo ago | ||
| nuPlan 14 Random (test) | CLS-NR0.948 | 49 | 4mo ago | ||
| Delicate Can (c) (test) | Time (s)0 | 48 | 4mo ago | ||
| PlanBench | Accuracy99.1 | 47 | 1mo ago | ||
| nuPlan 14 Hard (test) | Average Score94.03 | 46 | 1mo ago | ||
| NavSim (Navhard) | ForgeDrive | NC97.8 | 42 | 16d ago | |
| PushT | LeWM + AITS | Success Rate100 | 39 | 1mo ago | |
| nuScenes v1.0-trainval (val) | Senna | ST-P3 L2 Error (1s)0.11 | 39 | 2mo ago | |
| Blocksworld (test) | DeepSeek-R1 | Accuracy98.2 | 35 | 18d ago | |
| AutoLogic | Qwen3-Base (DICE-PC) | Accuracy89.1 | 34 | 1mo ago | |
| LIBERO Object Suite | V-VLAPS (both) | Average MCTS Simulations31.79 | 33 | 4mo ago | |
| LIBERO Spatial Suite | V-VLAPS (both) | Average MCTS Simulation28.8 | 33 | 4mo ago | |
| PDDL | GCD | Progress Rate100 | 33 | 1mo ago | |
| Navsim v2 (navtest) | FlowR2A | NC98.9 | 32 | 1mo ago | |
| 3D-Continuous Light-Dark | VOMCPOW | Mean Return4.8 | 30 | 2mo ago |