News Classification on AG News
87.2AccuracyGemini-2.5-Flash
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Gemini-2.5-FlashTask Model=Gemini-2.5-Flash2026.03 | 87.2 | 4.58 | 4.695 | 4.41 | |
| GPT-4o-miniTask Model=GPT-4o-mini2026.03 | 85.5 | 4.55 | 4.764 | 4.457 | |
| Llama-3-8BBackbone=Llama-3-8B2025.05 | 83.74 | — | — | — | |
| ASTRABackbone=Llama-3-8B, Group Size (G)=322025.05 | 83.25 | — | — | — | |
| ASTRABackbone=Llama-3-8B, Group Size (G)=162025.05 | 82.92 | — | — | — | |
| ASTRABackbone=Llama-3-8B, Group Size (G)=12025.05 | 78.52 | — | — | — | |
| Gemma-2-9B-ITTask Model=Gemma-2-9B-IT2026.03 | 59 | 4.063 | 4.223 | 4.061 | |
| Qwen-2.5-7B-ITTask Model=Qwen-2.5-7B-IT2026.03 | 56.3 | 4.048 | 4.75 | 4.209 | |
| LLaMA-3.1-8B-ITTask Model=LLaMA-3.1-8B-IT2026.03 | 55.6 | 3.845 | 4.656 | 3.958 |