List your company

Tool Use on Tool Use Live

56.25Para ScoreBase
36.7541.812546.87551.9375Jan 20, 2026

Evaluation results

MethodLinks
BaseModel Category=Base and Task Models2026.0156.2541.67
CURE (Coding)Model Category=Base and Task Models2026.0156.2537.5
ToolRL (Tool)Model Category=Base and Task Models2026.0156.2558.33
DARE+TIESModel Category=Merged Models2026.0156.2558.33
RAMModel Category=Merged Models2026.0156.2566.67
RAM+Model Category=Merged Models2026.0156.2570.83
WUDI2026.0156.2537.5
RAM2026.0156.2566.67
RAM+2026.0156.2570.83
DARE+TAModel Category=Merged Models2026.015062.5
DARE+TA2026.015062.5
TAModel Category=Merged Models2026.0143.7545.83
FisherModel Category=Merged Models2026.0143.7541.67
TIESModel Category=Merged Models2026.0143.7554.17
MemAgent (Memory)Model Category=Base and Task Models2026.0137.550