Question Answering on SciQ (Accuracy, Delta Accuracy)
72.8AccuracyAGoQ
Evaluation results
| Method | Links | ||
|---|---|---|---|
| AGoQModel=LLaMA2-7B, Training Tokens=2B tokens, Evaluation Protocol=Zero-shot2026.05 | 72.8 | 0.002 | |
| Megatron-LM FP16 BaselineModel=LLaMA2-7B, Training Tokens=2B tokens, Evaluation Protocol=Zero-shot2026.05 | 72.6 | — | |
| Megatron-LM FP16 BaselineModel=LLaMA3.2-1B, Training Tokens=10B tokens, Evaluation Protocol=Zero-shot2026.05 | 71.8 | — | |
| AGoQModel=LLaMA3.2-1B, Training Tokens=10B tokens, Evaluation Protocol=Zero-shot2026.05 | 71 | -0.008 |