Household Task Execution on AlfWorld (test)
97.01Success RateA-Mem
Evaluation Results
| Method | Links | |
|---|---|---|
| A-MemExecutor=Gemini-3-flash2026.05 | 97.01 | |
| A-MemExecutor=GPT-5.22026.05 | 92.54 | |
| No MemExecutor=Gemini-3-flash2026.05 | 92.54 | |
| LangMemExecutor=Gemini-3-flash2026.05 | 92.54 | |
| MemCompilerExecutor=Qwen-3.5-27B2026.05 | 91.45 | |
| Mem-0Executor=Gemini-3-flash2026.05 | 91.04 | |
| G-MemExecutor=Gemini-3-flash2026.05 | 90.3 | |
| A-MemExecutor=Qwen-3.5-27B2026.05 | 88.81 | |
| LangMemExecutor=GPT-5.22026.05 | 88.72 | |
| G-MemExecutor=GPT-5.22026.05 | 86.56 | |
| MemCompilerExecutor=Qwen-2.5-14B2026.05 | 82.16 | |
| Mem-0Executor=GPT-5.22026.05 | 76.12 | |
| G-MemExecutor=Qwen-3.5-27B2026.05 | 74.62 | |
| No MemExecutor=GPT-5.22026.05 | 70.89 | |
| G-MemExecutor=Qwen-2.5-14B2026.05 | 67.16 | |
| Mem-0Executor=Qwen-3.5-27B2026.05 | 62.69 | |
| LangMemExecutor=Qwen-3.5-27B2026.05 | 62.69 | |
| No MemExecutor=Qwen-3.5-27B2026.05 | 61.19 | |
| No MemExecutor=Qwen-2.5-14B2026.05 | 46.27 | |
| MemGenExecutor=Qwen-2.5-14B2026.05 | 42.54 | |
| MemGenExecutor=Qwen-3.5-27B2026.05 | 41.04 | |
| LangMemExecutor=Qwen-2.5-14B2026.05 | 36.57 | |
| Mem-0Executor=Qwen-2.5-14B2026.05 | 12.69 | |
| A-MemExecutor=Qwen-2.5-14B2026.05 | 11.19 |