List your company
ResearchFormerly WizWand

Execution Time on LoCoMo

21.7Execution Time (min)EFFGEN
2.752130.651258.55386.449Jan 31, 2026
Updated 8mo ago

Evaluation results

MethodLinks
EFFGENModel=Qwen2.5 (1.5B)2026.0121.7
Raw ModelModel=Qwen2.5 (3B)2026.0122.1
Raw ModelModel=Qwen2.5 (1.5B)2026.0125.5
EFFGENModel=Qwen2.5 (3B)2026.0128
EFFGENModel=Qwen2.5 (7B)2026.0130.1
Raw ModelModel=Qwen2.5 (7B)2026.0135.8
EFFGENModel=Qwen2.5 (14B)2026.0158.1
Raw ModelModel=Qwen2.5 (14B)2026.0164.7
LangChainModel=Qwen2.5 (1.5B)2026.0166.3
AutoGenModel=Qwen2.5 (1.5B)2026.0170.8
EFFGENModel=Qwen2.5 (32B)2026.0191.2
Raw ModelModel=Qwen2.5 (32B)2026.01109
AutoGenModel=Qwen2.5 (7B)2026.01110
SmolagentsModel=Qwen2.5 (1.5B)2026.01110.9
LangChainModel=Qwen2.5 (7B)2026.01143.1
LangChainModel=Qwen2.5 (3B)2026.01147.4
LangChainModel=Qwen2.5 (14B)2026.01148.5
AutoGenModel=Qwen2.5 (3B)2026.01157.7
AutoGenModel=Qwen2.5 (14B)2026.01184.9
SmolagentsModel=Qwen2.5 (3B)2026.01246.6
SmolagentsModel=Qwen2.5 (7B)2026.01254
LangChainModel=Qwen2.5 (32B)2026.01285.8
SmolagentsModel=Qwen2.5 (14B)2026.01304.9
AutoGenModel=Qwen2.5 (32B)2026.01314.4
SmolagentsModel=Qwen2.5 (32B)2026.01495.4