List your company

Reasoning on BBH 5-shot

75.69AccuracyERNIE 5.0-Base
69.845271.362672.8874.3974Feb 4, 2026

Evaluation results

MethodLinks
ERNIE 5.0-BaseNumber of shots=5-shot, Evaluation Protocol=Direct (w.o. CoT)2026.0275.69
DS V3.2-Exp-BaseNumber of shots=5-shot, Evaluation Protocol=Direct (w.o. CoT)2026.0273.5
Kimi K2-BaseNumber of shots=5-shot, Evaluation Protocol=Direct (w.o. CoT)2026.0270.07