Update README.md
Browse files
README.md
CHANGED
@@ -19,8 +19,41 @@ model-index:
|
|
19 |
type: thai_exam
|
20 |
metrics:
|
21 |
- name: Thai Exam (ACC)
|
22 |
-
type:
|
23 |
value: 63.89
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
source:
|
25 |
name: ๐น๐ญ 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: ๐น๐ญ Thai LLM Leaderboard
|
59 |
url: https://huggingface.co/spaces/ThaiLLM-Leaderboard/leaderboard
|