https://wandb.ai/open-assistant/supervised-finetuning/runs/lguuq2c1
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 47.44 |
| ARC (25-shot) | 57.94 |
| HellaSwag (10-shot) | 82.4 |
| MMLU (5-shot) | 48.56 |
| TruthfulQA (0-shot) | 47.27 |
| Winogrande (5-shot) | 76.87 |
| GSM8K (5-shot) | 8.26 |
| DROP (3-shot) | 10.81 |