List your company

Question Answering on WikidataQA BIG-bench 2023

71.9AccuracyEnsemble
63.99666.04868.170.152Jun 17, 2025

Evaluation results

MethodLinks
EnsembleAggregation Method=Byte-level Ensemble2025.0671.9
QWEN3Model=QWEN32025.0668.9
AverageAggregation Method=Average2025.0666.3
LLAMA3.2Model=LLAMA3.22025.0665.8
OLMO2Model=OLMO22025.0664.3