KnutJaegersberg leaderboard-pr-bot commited on
Commit
4dba777
1 Parent(s): 813c470

Adding Evaluation Results (#1)

Browse files

- Adding Evaluation Results (a1fa4c501ecbd57b09240509a60e470fb033d2f0)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +14 -1
README.md CHANGED
@@ -13,4 +13,17 @@ blablabla
13
  ### Input:
14
  (optional)
15
  ### Response:
16
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13
  ### Input:
14
  (optional)
15
  ### Response:
16
+ ```
17
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
18
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_KnutJaegersberg__MistralInstructLongish)
19
+
20
+ | Metric | Value |
21
+ |-----------------------|---------------------------|
22
+ | Avg. | 48.99 |
23
+ | ARC (25-shot) | 60.75 |
24
+ | HellaSwag (10-shot) | 81.86 |
25
+ | MMLU (5-shot) | 60.49 |
26
+ | TruthfulQA (0-shot) | 40.55 |
27
+ | Winogrande (5-shot) | 76.56 |
28
+ | GSM8K (5-shot) | 1.52 |
29
+ | DROP (3-shot) | 21.22 |