https://wandb.ai/open-assistant/supervised-finetuning/runs/shrzz3xp
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_dvruette__gpt-neox-20b-full-precision)

| Metric                | Value                     |
|-----------------------|---------------------------|
| Avg.                  | 37.62   |
| ARC (25-shot)         | 48.81          |
| HellaSwag (10-shot)   | 74.44    |
| MMLU (5-shot)         | 26.16         |
| TruthfulQA (0-shot)   | 36.89   |
| Winogrande (5-shot)   | 68.27   |
| GSM8K (5-shot)        | 2.65        |
| DROP (3-shot)         | 6.15         |