| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Two-Room | GC-IDM | Success Rate100 | 29 | 1mo ago | |
| GOAT-Bench | SCOPE | SR73.7 | 21 | 1mo ago | |
| D4RL antmaze | FINO | Score0.96 | 12 | 5mo ago | |
| OGBench antsoccer-arena-navigate | FINO | Score77 | 12 | 5mo ago | |
| OGBench antmaze-giant-navigate | ReBRAC | Score96 | 12 | 5mo ago | |
| OGBench antmaze-large-navigate | ReBRAC | Score99 | 12 | 5mo ago | |
| OGBench humanoidmaze-large-navigate | FINO | Score33 | 12 | 5mo ago | |
| OGBench humanoidmaze-medium-navigate | FINO | Score97 | 12 | 5mo ago | |
| Simulation Benchmark | FlowNav | Goal Reached Rate61 | 8 | 4mo ago | |
| Real-world corridor deployment 1.0 (test) | MetricNav | Success Rate96 | 7 | 4mo ago | |
| VEGA-Bench held-out (test) | OmniVLA | Goal Progress35 | 4 | 1mo ago | |
| MiniGrid 16x16 (RGB image input) (test) | TDRT-PPO | Clean Reward0.44 | 2 | 5mo ago | |
| MiniGrid 8x8 RGB image input (test) | TDRT-PPO | Clean Reward0.43 | 2 | 5mo ago |