List your company

Reasoning on BBH (Score, Delta, Avg. Rank)

80.1BBH ScoreQwen2.5(14B)T
30.80443.60256.469.198Jul 4, 2026

Evaluation results

MethodLinks
Qwen2.5(14B)TEvaluation Protocol=Generation-based2026.0780.1——
Qwen2.5(14B)TEvaluation Protocol=Likelihood-based2026.0751.71——
Qwen2.5(1.5B)SEvaluation Protocol=Generation-based2026.0747.0902.4
Reverse KLEvaluation Protocol=Generation-based2026.0744.52-2.573
RG-OPDEvaluation Protocol=Generation-based2026.0744.04-3.052
TSD-KDEvaluation Protocol=Likelihood-based2026.0737.961.772.6
TSD-KDEvaluation Protocol=Generation-based2026.0737.08-10.012.6
Qwen2.5(1.5B)SEvaluation Protocol=Likelihood-based2026.0736.1902.4
RG-OPDEvaluation Protocol=Likelihood-based2026.0734.4-1.792
Reverse KLEvaluation Protocol=Likelihood-based2026.0732.7-3.493