| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| EB-Habitat | ReAct | Avg Success Rate61.2 | 32 | 1mo ago | |
| ALFRED unseen (test) | Prompter | Success Rate4,572 | 14 | 1mo ago | |
| ALFRED seen (test) | Prompter | Success Rate (SR)53.23 | 14 | 1mo ago | |
| ALFWorld | ReAct | Success Rate94 | 9 | 1mo ago | |
| ALFRED EB | Gemma-3-12B-IT + µOffline Sup. | Avg Score32.2 | 8 | 1mo ago | |
| ALFRED Unseen (val) | Seq2Seq + PM R2VLM | Task Success Rate (TSR)20 | 3 | 1mo ago | |
| ALFRED seen (val) | Seq2Seq + PM R2VLM | Task Success Rate (SR)3.4 | 3 | 1mo ago | |
| ALFWorld out-of-distribution (test) | Meta-RL | Task Success Score (Cool)0.81 | 3 | 1mo ago | |
| ALFWorld in-distribution held-out (test) | Meta-RL | Pick Success97.7 | 3 | 1mo ago |