List your company

Multilingual Multiple Choice Question Answering on HellaSwag

54.6Accuracy (EN)Standard Evaluation
40.799244.382147.96551.5479Jun 9, 2026

Evaluation results

MethodLinks
Standard EvaluationScale=8B2026.0654.6531.6
ParaEvalScale=8B2026.0651.651.10.5
Standard EvaluationScale=3B2026.0649.448.11.3
ParaEvalScale=3B2026.0646.446.10.3
Standard EvaluationScale=1B2026.0644.3943.570.82
ParaEvalScale=1B2026.0641.3341.490.16