List your company

Question Answering on TriState-Bench

64.92EMARR
12.566426.158239.7553.3418Jun 9, 2026

Evaluation results

MethodLinks
ARRModel=Llama2-13B2026.0664.9269.37
ARRModel=Mistral-7B2026.0664.1770.28
ARRModel=Qwen2.5-7B2026.0663.2568.76
ARRModel=Llama3-8B2026.0661.6768.14
GreedyModel=Llama2-13B2026.0660.6765.4
AdaCADModel=Llama2-13B2026.0660.0864.96
GreedyModel=Mistral-7B2026.0659.7565.17
AdaCADModel=Mistral-7B2026.0658.8364.09
GreedyModel=Qwen2.5-7B2026.0658.8364.71
CoCoAModel=Llama2-13B2026.0655.7561.34
COIECDModel=Llama2-13B2026.065560.59
AdaCADModel=Qwen2.5-7B2026.0654.7561.67
COIECDModel=Mistral-7B2026.0652.9257.88
CADModel=Llama2-13B2026.0646.3354.61
GreedyModel=Llama3-8B2026.0642.9251.49
COIECDModel=Qwen2.5-7B2026.064151.92
AdaCADModel=Llama3-8B2026.0634.4244.76
CADModel=Mistral-7B2026.0631.9237.15
CoCoAModel=Mistral-7B2026.0629.3341.76
COIECDModel=Llama3-8B2026.0622.3334.87
CoCoAModel=Llama3-8B2026.0620.7533.7
CADModel=Qwen2.5-7B2026.0620.7537.38
CoCoAModel=Qwen2.5-7B2026.0619.1734.4
CADModel=Llama3-8B2026.0614.5828.7