Adding Evaluation Results
#16
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -100,3 +100,17 @@ Please cite the repo if you use the data, method or code in this repo.
|
|
| 100 |
year={2023}
|
| 101 |
}
|
| 102 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 100 |
year={2023}
|
| 101 |
}
|
| 102 |
```
|
| 103 |
+
|
| 104 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 105 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_WizardLM__WizardMath-70B-V1.0)
|
| 106 |
+
|
| 107 |
+
| Metric | Value |
|
| 108 |
+
|-----------------------|---------------------------|
|
| 109 |
+
| Avg. | 54.41 |
|
| 110 |
+
| ARC (25-shot) | 68.17 |
|
| 111 |
+
| HellaSwag (10-shot) | 86.49 |
|
| 112 |
+
| MMLU (5-shot) | 68.89 |
|
| 113 |
+
| TruthfulQA (0-shot) | 52.69 |
|
| 114 |
+
| Winogrande (5-shot) | 82.32 |
|
| 115 |
+
| GSM8K (5-shot) | 3.94 |
|
| 116 |
+
| DROP (3-shot) | 18.37 |
|