Accuracy on SQuAD v1.1
37.8AccuracyAMATA 8B
Evaluation Results
| Method | Links | |
|---|---|---|
| AMATA 8BModel Scale=8B, Backbone Architecture=AMATA2026.05 | 37.8 | |
| SPA-RL 8BModel Scale=8B, Backbone Architecture=SPA-RL2026.05 | 34.51 | |
| GiGPO 8BModel Scale=8B, Backbone Architecture=GiGPO2026.05 | 34.05 | |
| SMART 8BModel Scale=8B, Backbone Architecture=SMART2026.05 | 33.05 | |
| SelfRag 8BModel Scale=8B, Backbone Architecture=Self-RAG2026.05 | 26.06 | |
| RADIT 8BModel Scale=8B, Backbone Architecture=RADIT2026.05 | 24.97 | |
| GPT4oBackbone Architecture=GPT-4o2026.05 | 24.83 | |
| Llama-3-Ins.8BModel Scale=8B, Backbone Architecture=Llama-3-Ins2026.05 | 16.24 |