List your company

Question Answering on BoolQ (Perf., #D, Sp.)

87.63PerformanceBest Model
82.190883.602985.01586.4271Oct 26, 2025

Evaluation results

MethodLinks
Best Modelshot=0-shot, eval_tool=LM Eval2025.1087.633-8.8
BSBAshot=0-shot, eval_tool=LM Eval2025.1085.627-20.5
LLaMA 3.1 8B Baselineshot=0-shot, eval_tool=LM Eval2025.1082.4——