List your company

Logical reasoning multi-choice QA on LogiQA v2 (test)

55.5Macro F1 ScoreT5-large
29.104835.957442.8149.6626Feb 17, 2025

Evaluation results

MethodLinks
T5-largeWarmup=true2025.0255.555.62
T5-largeWarmup=false2025.0254.4654.54
T5-baseWarmup=true2025.025050.06
T5-baseWarmup=false2025.0249.1649.19
Llama-3.2-1BWarmup=true2025.0232.6333.55
Llama-3.2-1BWarmup=false2025.0230.1231.7