List your company

Safety on XSTest (Normalized performance)

1.245Normalized PerformanceMETIS
0.629320.789160.9491.10884Jun 15, 2026

Evaluation results

MethodLinks
METISCategory=Ours, Backbone=Llama-3.2-3B2026.061.245
TSV-MCategory=State-of-the-Art (+Many-shot), Backbone=Llama-3.2-3B2026.061.184
ConsensusTACategory=Conventional Method (+Many-shot), Backbone=Llama-3.2-3B2026.061.163
TIESCategory=Conventional Method (+Many-shot), Backbone=Llama-3.2-3B2026.061.143
TULU 3Category=Data-Mixing, Backbone=Llama-3.2-3B2026.061.102
DARECategory=Conventional Method (+Many-shot), Backbone=Llama-3.2-3B2026.060.98
TA + Subspace BoostingCategory=State-of-the-Art (+Many-shot), Backbone=Llama-3.2-3B2026.060.959
Task ArithmeticCategory=Conventional Method (+Many-shot), Backbone=Llama-3.2-3B2026.060.878
ColD FusionCategory=Iterative / FL, Backbone=Llama-3.2-3B2026.060.857
Iso-CCategory=State-of-the-Art (+Many-shot), Backbone=Llama-3.2-3B2026.060.837
q-FedAvgCategory=Iterative / FL, Backbone=Llama-3.2-3B2026.060.837
FedMergeCategory=Iterative / FL, Backbone=Llama-3.2-3B2026.060.796
Iso-CTSCategory=State-of-the-Art (+Many-shot), Backbone=Llama-3.2-3B2026.060.653