Spaces:
Sleeping
Sleeping
Update big.json
Browse files
big.json
CHANGED
@@ -1,68 +1,88 @@
|
|
1 |
[
|
|
|
|
|
2 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
"model": "GPT-4",
|
4 |
-
"Average": 65.
|
5 |
-
"MMLU": 74.
|
6 |
-
"
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"
|
11 |
-
"
|
|
|
12 |
},
|
13 |
{
|
14 |
"model": "Claude-3 Opus",
|
15 |
-
"Average": 62.
|
16 |
-
"MMLU": 70.
|
17 |
-
"
|
18 |
-
"
|
19 |
-
"
|
20 |
-
"
|
21 |
-
"
|
22 |
-
"
|
|
|
23 |
},
|
24 |
{
|
25 |
"model": "Mistral Large",
|
26 |
-
"Average":
|
27 |
-
"MMLU":
|
28 |
-
"
|
29 |
-
"
|
30 |
-
"
|
31 |
-
"
|
32 |
-
"
|
33 |
-
"
|
|
|
34 |
},
|
35 |
{
|
36 |
"model": "GPT-3.5",
|
37 |
-
"Average":
|
38 |
-
"MMLU": 65.
|
39 |
-
|
40 |
-
"
|
41 |
-
"
|
42 |
-
"
|
43 |
-
"
|
44 |
-
"
|
|
|
45 |
},
|
46 |
{
|
47 |
-
"model": "Gemini Pro",
|
48 |
-
"Average": 54.
|
49 |
-
"MMLU":
|
50 |
-
"
|
51 |
-
"
|
52 |
-
"
|
53 |
-
"
|
54 |
-
"
|
55 |
-
"
|
|
|
56 |
},
|
57 |
{
|
58 |
"model": "Llama3-70b-instruct",
|
59 |
-
"Average":
|
60 |
-
"MMLU":
|
|
|
61 |
"WinoGrande": 57.14,
|
62 |
-
"PiQA": 43.
|
63 |
"CommonsenseQA": 55.49,
|
64 |
"Race": 58.21,
|
65 |
"MedMCQA": 41.67,
|
66 |
-
"OpenkookQA":
|
67 |
}
|
68 |
]
|
|
|
1 |
[
|
2 |
+
|
3 |
+
|
4 |
{
|
5 |
+
"model": "GPT-4o",
|
6 |
+
"Average": 70.15,
|
7 |
+
"MMLU": 70.09,
|
8 |
+
"ARC":86.33,
|
9 |
+
"WinoGrande:"72.22,
|
10 |
+
"PiQA":60.34,
|
11 |
+
"CommonsenseQA":70.28,
|
12 |
+
"Race":67.87 ,
|
13 |
+
"MedMCQA":57.85 ,
|
14 |
+
"OpenkookQA":67.21
|
15 |
+
},
|
16 |
+
{
|
17 |
"model": "GPT-4",
|
18 |
+
"Average": 65.93,
|
19 |
+
"MMLU": 74.77,
|
20 |
+
"ARC":82.68,
|
21 |
+
"WinoGrande": 66.22,
|
22 |
+
"PiQA": 61.64,
|
23 |
+
"CommonsenseQA": 62.96,
|
24 |
+
"Race": 67.05,
|
25 |
+
"MedMCQA": 51.81,
|
26 |
+
"OpenkookQA": 60.29
|
27 |
},
|
28 |
{
|
29 |
"model": "Claude-3 Opus",
|
30 |
+
"Average": 62.68,
|
31 |
+
"MMLU": 70.23,
|
32 |
+
"ARC":76.62,
|
33 |
+
"WinoGrande": 63.54,
|
34 |
+
"PiQA": 59.05,
|
35 |
+
"CommonsenseQA": 63.66,
|
36 |
+
"Race": 66.22,
|
37 |
+
"MedMCQA": 49.14,
|
38 |
+
"OpenkookQA": 52.95
|
39 |
},
|
40 |
{
|
41 |
"model": "Mistral Large",
|
42 |
+
"Average": 60.48,
|
43 |
+
"MMLU": 68.76,
|
44 |
+
"ARC":72.32
|
45 |
+
"WinoGrande": 56.83,
|
46 |
+
"PiQA": 61.21,
|
47 |
+
"CommonsenseQA": 55.35,
|
48 |
+
"Race": 70.17,
|
49 |
+
"MedMCQA": 43.44,
|
50 |
+
"OpenkookQA": 58.66
|
51 |
},
|
52 |
{
|
53 |
"model": "GPT-3.5",
|
54 |
+
"Average": 60.30,
|
55 |
+
"MMLU": 65.38,
|
56 |
+
"ARC":78.24,
|
57 |
+
"WinoGrande": 64.56,
|
58 |
+
"PiQA": 54.89,
|
59 |
+
"CommonsenseQA": 67.89,
|
60 |
+
"Race": 60.11,
|
61 |
+
"MedMCQA": 41.42,
|
62 |
+
"OpenkookQA": 49.90
|
63 |
},
|
64 |
{
|
65 |
+
"model": "Gemini 1.0 Pro",
|
66 |
+
"Average": 54.04,
|
67 |
+
"MMLU": 56.04,
|
68 |
+
"ARC":72.23,
|
69 |
+
"WinoGrande": 56.35,
|
70 |
+
"PiQA": 47.70,
|
71 |
+
"CommonsenseQA": 50.56,
|
72 |
+
"Race": 61.02,
|
73 |
+
"MedMCQA": 35.89,
|
74 |
+
"OpenkookQA": 52.55
|
75 |
},
|
76 |
{
|
77 |
"model": "Llama3-70b-instruct",
|
78 |
+
"Average": 52.92,
|
79 |
+
"MMLU": 59.67,
|
80 |
+
"ARC":67.09,
|
81 |
"WinoGrande": 57.14,
|
82 |
+
"PiQA": 43.10,
|
83 |
"CommonsenseQA": 55.49,
|
84 |
"Race": 58.21,
|
85 |
"MedMCQA": 41.67,
|
86 |
+
"OpenkookQA": 40.94
|
87 |
}
|
88 |
]
|