List your company

Instruction Following on BabyAI

72.56Success RateAgeMem
45.291252.370659.4566.5294Jan 5, 2026

Evaluation results

MethodLinks
AgeMemLLM Backbone=Qwen3-4B-Instruct2026.0172.5654.31
AgeMemLLM Backbone=Qwen2.5-7B-Instruct2026.0161.4241.96
A-MemLLM Backbone=Qwen3-4B-Instruct2026.0161.3545.74
Mem0LLM Backbone=Qwen2.5-7B-Instruct2026.0160.5837.14
Mem0LLM Backbone=Qwen3-4B-Instruct2026.0160.0544.7
A-MemLLM Backbone=Qwen2.5-7B-Instruct2026.0158.8236.78
Mem0gLLM Backbone=Qwen2.5-7B-Instruct2026.0158.7836.31
Mem0gLLM Backbone=Qwen3-4B-Instruct2026.0157.5941.95
AgeMem-noRLLLM Backbone=Qwen3-4B-Instruct2026.0157.4845.59
No-MemoryLLM Backbone=Qwen3-4B-Instruct2026.0155.8343.97
LangMemLLM Backbone=Qwen3-4B-Instruct2026.0153.843.25
LangMemLLM Backbone=Qwen2.5-7B-Instruct2026.0151.3434.23
No-MemoryLLM Backbone=Qwen2.5-7B-Instruct2026.0150.828.05
AgeMem-noRLLLM Backbone=Qwen2.5-7B-Instruct2026.0146.3433.43