List your company

Household Task Execution on AlfWorld (test)

97.01Success RateA-Mem
7.757230.928654.177.2714May 8, 2026

Evaluation results

MethodLinks
A-MemExecutor=Gemini-3-flash2026.0597.01
A-MemExecutor=GPT-5.22026.0592.54
No MemExecutor=Gemini-3-flash2026.0592.54
LangMemExecutor=Gemini-3-flash2026.0592.54
MemCompilerExecutor=Qwen-3.5-27B2026.0591.45
Mem-0Executor=Gemini-3-flash2026.0591.04
G-MemExecutor=Gemini-3-flash2026.0590.3
A-MemExecutor=Qwen-3.5-27B2026.0588.81
LangMemExecutor=GPT-5.22026.0588.72
G-MemExecutor=GPT-5.22026.0586.56
MemCompilerExecutor=Qwen-2.5-14B2026.0582.16
Mem-0Executor=GPT-5.22026.0576.12
G-MemExecutor=Qwen-3.5-27B2026.0574.62
No MemExecutor=GPT-5.22026.0570.89
G-MemExecutor=Qwen-2.5-14B2026.0567.16
Mem-0Executor=Qwen-3.5-27B2026.0562.69
LangMemExecutor=Qwen-3.5-27B2026.0562.69
No MemExecutor=Qwen-3.5-27B2026.0561.19
No MemExecutor=Qwen-2.5-14B2026.0546.27
MemGenExecutor=Qwen-2.5-14B2026.0542.54
MemGenExecutor=Qwen-3.5-27B2026.0541.04
LangMemExecutor=Qwen-2.5-14B2026.0536.57
Mem-0Executor=Qwen-2.5-14B2026.0512.69
A-MemExecutor=Qwen-2.5-14B2026.0511.19