Commit
•
5737b53
1
Parent(s):
08239fb
Adding Evaluation Results (#2)
Browse files- Adding Evaluation Results (4d405e1de639a5ee3e060f42adf5dbde1c5e2828)
Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>
README.md
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
3 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_chargoddard__MelangeB-70b)
|
4 |
+
|
5 |
+
| Metric | Value |
|
6 |
+
|-----------------------|---------------------------|
|
7 |
+
| Avg. | 65.8 |
|
8 |
+
| ARC (25-shot) | 71.67 |
|
9 |
+
| HellaSwag (10-shot) | 87.5 |
|
10 |
+
| MMLU (5-shot) | 70.03 |
|
11 |
+
| TruthfulQA (0-shot) | 59.36 |
|
12 |
+
| Winogrande (5-shot) | 83.5 |
|
13 |
+
| GSM8K (5-shot) | 30.63 |
|
14 |
+
| DROP (3-shot) | 57.92 |
|