MedicalBenchmark
Baidu: ERNIE 4.5 21B A3B provider

ERNIE 4.5 21B A3B

230

#230 of 291 modelsMIR 2024

Net score

125.66 pts

Accuracy

71.5%

Correct / Incorrect

143 / 52

Total Cost

$0.04

Overall Performance

(vs. average)
Accuracy

71.5%

avg: 80.5%

Net score

125.66 pts

avg: 150.85 pts

Correct

143

avg: 161

Incorrect

52

avg: 30

Total Cost

$0.04

avg: $3.32

Average response time

6.7s

avg: 16.4s

Output Tokens

106K

avg: 427K

Reasoning Tokens

0

avg: 310K

Average confidence

96.0%

avg: 95.4%

Subject Breakdown

Allergology
Correct
3
Incorrect
0
Unanswered
0
Accuracy
100.0%
Average
90.5%
Anesthesiology and Resuscitation
Correct
3
Incorrect
0
Unanswered
1
Accuracy
75.0%
Average
87.1%
Cardiology
Correct
13
Incorrect
8
Unanswered
0
Accuracy
61.9%
Average
79.7%
Dermatology
Correct
11
Incorrect
3
Unanswered
0
Accuracy
78.6%
Average
80.2%
Endocrinology and Nutrition
Correct
16
Incorrect
2
Unanswered
1
Accuracy
84.2%
Average
84.2%
ENT
Correct
4
Incorrect
3
Unanswered
0
Accuracy
57.1%
Average
74.4%
Epidemiology
Correct
7
Incorrect
0
Unanswered
1
Accuracy
87.5%
Average
89.3%
Gastroenterology
Correct
15
Incorrect
7
Unanswered
0
Accuracy
68.2%
Average
70.5%
Genetics
Correct
4
Incorrect
3
Unanswered
0
Accuracy
57.1%
Average
86.5%
Geriatrics
Correct
8
Incorrect
2
Unanswered
0
Accuracy
80.0%
Average
86.9%
Gynecology and Obstetrics
Correct
9
Incorrect
5
Unanswered
0
Accuracy
64.3%
Average
81.2%
Health Planning and Management
Correct
1
Incorrect
1
Unanswered
0
Accuracy
50.0%
Average
73.2%
Hematology
Correct
9
Incorrect
4
Unanswered
0
Accuracy
69.2%
Average
81.5%
Immunology
Correct
4
Incorrect
1
Unanswered
3
Accuracy
50.0%
Average
89.1%
Infectious Diseases
Correct
14
Incorrect
7
Unanswered
2
Accuracy
60.9%
Average
81.8%
Legal Medicine and Bioethics
Correct
2
Incorrect
0
Unanswered
0
Accuracy
100.0%
Average
91.7%
Medical Oncology
Correct
14
Incorrect
6
Unanswered
1
Accuracy
66.7%
Average
80.2%
Nephrology
Correct
11
Incorrect
2
Unanswered
0
Accuracy
84.6%
Average
80.8%
Neurology
Correct
16
Incorrect
6
Unanswered
0
Accuracy
72.7%
Average
83.7%
Ophthalmology
Correct
4
Incorrect
1
Unanswered
0
Accuracy
80.0%
Average
80.0%
Palliative Care
Correct
4
Incorrect
0
Unanswered
0
Accuracy
100.0%
Average
88.2%
Pediatrics
Correct
10
Incorrect
7
Unanswered
0
Accuracy
58.8%
Average
82.0%
Pharmacology
Correct
21
Incorrect
2
Unanswered
0
Accuracy
91.3%
Average
85.4%
Psychiatry
Correct
8
Incorrect
1
Unanswered
1
Accuracy
80.0%
Average
89.5%
Pulmonology
Correct
14
Incorrect
5
Unanswered
0
Accuracy
73.7%
Average
80.6%
Radiology-Emergency
Correct
7
Incorrect
7
Unanswered
0
Accuracy
50.0%
Average
64.9%
Rheumatology
Correct
11
Incorrect
3
Unanswered
0
Accuracy
78.6%
Average
81.4%
Statistics
Correct
3
Incorrect
0
Unanswered
0
Accuracy
100.0%
Average
91.1%
Traumatology
Correct
9
Incorrect
6
Unanswered
0
Accuracy
60.0%
Average
74.5%
Urology
Correct
5
Incorrect
1
Unanswered
0
Accuracy
83.3%
Average
78.2%

Question Type Breakdown

Anatomy
Correct
4
Incorrect
2
Unanswered
0
Accuracy
66.7%
Average
79.8%
Biostatistics
Correct
5
Incorrect
0
Unanswered
0
Accuracy
100.0%
Average
90.7%
Diagnosis
Correct
56
Incorrect
17
Unanswered
0
Accuracy
76.7%
Average
79.2%
Epidemiology
Correct
7
Incorrect
4
Unanswered
1
Accuracy
58.3%
Average
81.2%
Ethics
Correct
1
Incorrect
0
Unanswered
0
Accuracy
100.0%
Average
94.5%
Interpretation
Correct
18
Incorrect
19
Unanswered
0
Accuracy
48.6%
Average
69.6%
Pathophysiology
Correct
25
Incorrect
6
Unanswered
2
Accuracy
75.8%
Average
85.4%
Pharmacology
Correct
19
Incorrect
4
Unanswered
2
Accuracy
76.0%
Average
84.0%
Prevention
Correct
10
Incorrect
0
Unanswered
2
Accuracy
83.3%
Average
89.8%
Prognosis
Correct
5
Incorrect
2
Unanswered
0
Accuracy
71.4%
Average
83.9%
Risk
Correct
9
Incorrect
3
Unanswered
1
Accuracy
69.2%
Average
83.6%
Tests
Correct
14
Incorrect
7
Unanswered
0
Accuracy
66.7%
Average
73.9%
Treatment
Correct
52
Incorrect
18
Unanswered
1
Accuracy
73.2%
Average
81.3%
#AnswerCorrectStatus
1AB
2DD
3AB
4AC
5BC
6BB
7DD
8BC
9BA
10BD
11DD
12AA
13BC
14DA
15AB
16AA
17CC
18AA
19BB
20AC
21CD
22BB
23AA
24CA
25CC
26BB
27CC
28AA
29BB
30AC
31BD
32BA
33CC
34DB
35D
36DD
37A
38A
39CC
40BB
41CC
42DD
43AA
44DD
45DD
46BB
47CC
48CC
49BB
50BC
51AA
52DD
53CC
54BB
55CC
56DD
57CA
58DA
59AA
60AA
61DA
62BD
63DD
64BAnnulled
65DD
66CC
67DB
68BAnnulled
69AA
70BB
71BB
72BD
73CB
74CC
75BB
76AA
77CD
78CC
79DB
80AA
81CC
82CC
83B
84CC
85AA
86AA
87CB
88DD
89BB
90AA
91DD
92AA
93CC
94BB
95CD
96BB
97BB
98BB
99BA
100CB
101AA
102DD
103BB
104DD
105DB
106BC
107CC
108BB
109DD
110DD
111CB
112CC
113DAnnulled
114DD
115DD
116AA
117DD
118DD
119CA
120CC
121AA
122DB
123DD
124DD
125BB
126DD
127BA
128BB
129DD
130DC
131CC
132DD
133CA
134BC
135BA
136DD
137AA
138CC
139AA
140C
141BB
142CC
143DA
144DD
145CC
146BC
147CC
148AA
149AC
150DD
151CA
152AA
153CC
154BB
155DD
156AC
157CC
158DD
159DD
160CB
161BB
162BB
163BB
164DB
165AA
166CC
167CA
168BB
169CC
170CA
171DD
172BB
173CA
174BB
175AA
176CC
177CC
178BB
179CC
180BAnnulled
181BB
182DD
183CC
184AA
185CC
186DD
187AA
188CC
189AD
190DD
191BB
192BB
193CC
194CC
195CC
196BB
197AA
198BB
199DD
200AA
201BB
202DD
203BB
204DD
205BD
206BAnnulled
207AA
208AA
209AB
210DD