Spaces:
Sleeping
Sleeping
Update ShoppingMMLU_overall.json
Browse files- ShoppingMMLU_overall.json +38 -0
ShoppingMMLU_overall.json
CHANGED
@@ -1,6 +1,44 @@
|
|
1 |
{
|
2 |
"time": "241111120000",
|
3 |
"results": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
"Claude-2": {
|
5 |
"META": {
|
6 |
"Method": [
|
|
|
1 |
{
|
2 |
"time": "241111120000",
|
3 |
"results": {
|
4 |
+
"Task-specific SOTA": {
|
5 |
+
"META": {
|
6 |
+
"Method": [
|
7 |
+
"Task-specific SOTA"
|
8 |
+
],
|
9 |
+
"Parameters": "",
|
10 |
+
"Org": "",
|
11 |
+
"OpenSource": "No",
|
12 |
+
"Verified": "Yes"
|
13 |
+
},
|
14 |
+
"MedQA": {
|
15 |
+
"Overall": 44.6
|
16 |
+
},
|
17 |
+
"MedMCQA": {
|
18 |
+
"Overall": 43.0
|
19 |
+
},
|
20 |
+
"MMLU-Medicine": {
|
21 |
+
"Overall": 60.2
|
22 |
+
},
|
23 |
+
"PubMedQA": {
|
24 |
+
"Overall": 60.2
|
25 |
+
},
|
26 |
+
"BC5": {
|
27 |
+
"Overall": 90.0
|
28 |
+
},
|
29 |
+
"NCBI": {
|
30 |
+
"Overall": 89.4
|
31 |
+
},
|
32 |
+
"DDI": {
|
33 |
+
"Overall": 84.1
|
34 |
+
},
|
35 |
+
"GAD": {
|
36 |
+
"Overall": 84.0
|
37 |
+
},
|
38 |
+
"HoC": {
|
39 |
+
"Overall": 85.1
|
40 |
+
}
|
41 |
+
},
|
42 |
"Claude-2": {
|
43 |
"META": {
|
44 |
"Method": [
|