List your company

Context-aware generation on TriState-Bench Agreement Sagr gold context, prior correct

93.75Exact Match (EM)Greedy
18.3537.92557.577.075Jun 9, 2026

Evaluation results

MethodLinks
GreedyModel=Llama2-13B2026.0693.7595.83
ARRModel=Llama2-13B2026.0693.7595.81
AdaCADModel=Llama2-13B2026.0693.2595.4
ARRModel=Qwen2.5-7B2026.0688.2592.27
GreedyModel=Qwen2.5-7B2026.068690.76
CoCoAModel=Llama2-13B2026.0685.589.46
COIECDModel=Llama2-13B2026.068488.25
AdaCADModel=Mistral-7B2026.0683.2587.95
GreedyModel=Mistral-7B2026.0682.7587.76
AdaCADModel=Qwen2.5-7B2026.0682.2588.56
ARRModel=Mistral-7B2026.068287.46
ARRModel=Llama3-8B2026.0676.7583.15
COIECDModel=Mistral-7B2026.0672.7575.56
CADModel=Llama2-13B2026.0672.580.35
GreedyModel=Llama3-8B2026.0664.7573.92
COIECDModel=Qwen2.5-7B2026.0656.7571.96
AdaCADModel=Llama3-8B2026.0648.560.43
CADModel=Qwen2.5-7B2026.0636.2556.18
COIECDModel=Llama3-8B2026.063550.99
CoCoAModel=Mistral-7B2026.063248.19
CoCoAModel=Qwen2.5-7B2026.0630.7550.6
CoCoAModel=Llama3-8B2026.063045.52
CADModel=Mistral-7B2026.062527.51
CADModel=Llama3-8B2026.0621.2537.92