https://wandb.ai/open-assistant/supervised-finetuning/runs/uwqcwaau
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 35.69 |
ARC (25-shot) | 44.97 |
HellaSwag (10-shot) | 69.75 |
MMLU (5-shot) | 26.64 |
TruthfulQA (0-shot) | 38.89 |
Winogrande (5-shot) | 63.14 |
GSM8K (5-shot) | 0.99 |
DROP (3-shot) | 5.48 |