Adding Evaluation Results
#18
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -32,4 +32,17 @@ For roleplay purposes, I suggest the following - Write <CHAR NAME>'s next reply
|
|
| 32 |
|
| 33 |
---
|
| 34 |
license: other
|
| 35 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
|
| 33 |
---
|
| 34 |
license: other
|
| 35 |
+
---
|
| 36 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 37 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Gryphe__MythoMax-L2-13b)
|
| 38 |
+
|
| 39 |
+
| Metric | Value |
|
| 40 |
+
|-----------------------|---------------------------|
|
| 41 |
+
| Avg. | 50.97 |
|
| 42 |
+
| ARC (25-shot) | 60.92 |
|
| 43 |
+
| HellaSwag (10-shot) | 83.56 |
|
| 44 |
+
| MMLU (5-shot) | 55.33 |
|
| 45 |
+
| TruthfulQA (0-shot) | 51.97 |
|
| 46 |
+
| Winogrande (5-shot) | 75.22 |
|
| 47 |
+
| GSM8K (5-shot) | 9.02 |
|
| 48 |
+
| DROP (3-shot) | 20.73 |
|