kobkrit commited on
Commit
a4425e5
ยท
verified ยท
1 Parent(s): 4c273a7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +34 -1
README.md CHANGED
@@ -19,8 +19,41 @@ model-index:
19
  type: thai_exam
20
  metrics:
21
  - name: Thai Exam (ACC)
22
- type: Thai Exam (ACC)
23
  value: 63.89
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
24
  source:
25
  name: ๐Ÿ‡น๐Ÿ‡ญ Thai LLM Leaderboard
26
  url: https://huggingface.co/spaces/ThaiLLM-Leaderboard/leaderboard
 
19
  type: thai_exam
20
  metrics:
21
  - name: Thai Exam (ACC)
22
+ type: accuracy
23
  value: 63.89
24
+ - name: M3Exam (ACC)
25
+ type: accuracy
26
+ value: 70.39
27
+ - name: Average Accuracy
28
+ type: accuracy
29
+ value: 70.15
30
+ - name: MT-Bench Knowledge Rating
31
+ type: rating
32
+ value: 4.85
33
+ - name: MT-Bench Social Science Rating
34
+ type: rating
35
+ value: 8.65
36
+ - name: MT-Bench Extraction Rating
37
+ type: rating
38
+ value: 6.5
39
+ - name: MT-Bench Math Rating
40
+ type: rating
41
+ value: 8.05
42
+ - name: MT-Bench Reasoning Rating
43
+ type: rating
44
+ value: 6.6
45
+ - name: MT-Bench STEM Rating
46
+ type: rating
47
+ value: 7.35
48
+ - name: MT-Bench Writing Rating
49
+ type: rating
50
+ value: 6.45
51
+ - name: MT-Bench Coding Rating
52
+ type: rating
53
+ value: 7.95
54
+ - name: MT-Bench Roleplay Rating
55
+ type: rating
56
+ value: 7
57
  source:
58
  name: ๐Ÿ‡น๐Ÿ‡ญ Thai LLM Leaderboard
59
  url: https://huggingface.co/spaces/ThaiLLM-Leaderboard/leaderboard