List your company

Question Answering on TruthfulQA (Accuracy, Standard Deviation)

81.62AccuracyROAST
21.14436.844552.54568.2455Feb 15, 2026

Evaluation results

MethodLinks
ROASTModel=Qwen3-8B, Training Size=1000, Aggregation=group2026.0281.623
ROASTModel=Qwen3-0.6B, Training Size=1000, Aggregation=group2026.0249.9123
ROASTModel=Gemma3-1B, Training Size=1000, Aggregation=group2026.0223.47357