List your company

News Classification on AG News

87.2AccuracyGemini-2.5-Flash
54.33662.86871.479.932May 25, 2025Jul 12, 2025Aug 29, 2025Oct 17, 2025Dec 4, 2025Jan 21, 2026Mar 11, 2026

Evaluation results

MethodLinks
Gemini-2.5-FlashTask Model=Gemini-2.5-Flash2026.0387.24.584.6954.41
GPT-4o-miniTask Model=GPT-4o-mini2026.0385.54.554.7644.457
Llama-3-8BBackbone=Llama-3-8B2025.0583.74———
ASTRABackbone=Llama-3-8B, Group Size (G)=322025.0583.25———
ASTRABackbone=Llama-3-8B, Group Size (G)=162025.0582.92———
ASTRABackbone=Llama-3-8B, Group Size (G)=12025.0578.52———
Gemma-2-9B-ITTask Model=Gemma-2-9B-IT2026.03594.0634.2234.061
Qwen-2.5-7B-ITTask Model=Qwen-2.5-7B-IT2026.0356.34.0484.754.209
LLaMA-3.1-8B-ITTask Model=LLaMA-3.1-8B-IT2026.0355.63.8454.6563.958