license: apache-2.0 | |
Please see our [LLMZoo](https://github.com/FreedomIntelligence/LLMZoo) project: https://github.com/FreedomIntelligence/LLMZoo. | |
# [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_FreedomIntelligence__phoenix-inst-chat-7b) | |
| Metric | Value | | |
|-----------------------|---------------------------| | |
| Avg. | 40.69 | | |
| ARC (25-shot) | 44.71 | | |
| HellaSwag (10-shot) | 63.23 | | |
| MMLU (5-shot) | 39.06 | | |
| TruthfulQA (0-shot) | 47.08 | | |
| Winogrande (5-shot) | 62.83 | | |
| GSM8K (5-shot) | 1.29 | | |
| DROP (3-shot) | 26.62 | | |