Sao10K leaderboard-pr-bot commited on
Commit
b2a9b33
1 Parent(s): 7c273cb

Adding Evaluation Results (#1)

Browse files

- Adding Evaluation Results (6f3989af84fa8b9119f1933ed369fd7638116417)


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
@@ -24,4 +24,17 @@ i can easily steal the top leaderboard spots but meh not worth the effort.
24
 
25
  that's it. i didn't bother testing much. ymmv.
26
 
27
- <img src="https://blog.cdn.own3d.tv/resize=fit:crop,height:400,width:600/tbv2RYWpReqNtof2dD0U" style="width: 70%; min-width: 300px; display: block; margin: auto;">
 
 
 
 
 
 
 
 
 
 
 
 
 
 
24
 
25
  that's it. i didn't bother testing much. ymmv.
26
 
27
+ <img src="https://blog.cdn.own3d.tv/resize=fit:crop,height:400,width:600/tbv2RYWpReqNtof2dD0U" style="width: 70%; min-width: 300px; display: block; margin: auto;">
28
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
29
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Sao10K__BrainDerp2)
30
+
31
+ | Metric | Value |
32
+ |-----------------------|---------------------------|
33
+ | Avg. | 51.18 |
34
+ | ARC (25-shot) | 60.92 |
35
+ | HellaSwag (10-shot) | 81.94 |
36
+ | MMLU (5-shot) | 58.9 |
37
+ | TruthfulQA (0-shot) | 57.19 |
38
+ | Winogrande (5-shot) | 75.93 |
39
+ | GSM8K (5-shot) | 9.02 |
40
+ | DROP (3-shot) | 14.34 |