MedicalBenchmark
Microsoft: Phi 4 provider

Phi 4

238

#238 of 290 modelsMIR 2026

Net score

117.33 pts

Accuracy

68.5%

Correct / Incorrect

137 / 59

Total Cost

$0.02

Overall Performance

(vs. average)
Accuracy

68.5%

avg: 81.6%

Net score

117.33 pts

avg: 154.00 pts

Correct

137

avg: 163

Incorrect

59

avg: 28

Total Cost

$0.02

avg: $3.33

Average response time

12.6s

avg: 16.2s

Output Tokens

129K

avg: 430K

Reasoning Tokens

0

avg: 310K

Average confidence

95.7%

avg: 95.1%

Subject Breakdown

Allergology
Correct
1
Incorrect
0
Unanswered
0
Accuracy
100.0%
Average
96.9%
Anesthesiology and Resuscitation
Correct
2
Incorrect
5
Unanswered
0
Accuracy
28.6%
Average
69.6%
Cardiology
Correct
16
Incorrect
9
Unanswered
0
Accuracy
64.0%
Average
77.3%
Dermatology
Correct
7
Incorrect
4
Unanswered
0
Accuracy
63.6%
Average
72.3%
Endocrinology and Nutrition
Correct
12
Incorrect
3
Unanswered
0
Accuracy
80.0%
Average
84.0%
ENT
Correct
4
Incorrect
4
Unanswered
0
Accuracy
50.0%
Average
84.7%
Epidemiology
Correct
5
Incorrect
0
Unanswered
2
Accuracy
71.4%
Average
80.2%
Gastroenterology
Correct
17
Incorrect
13
Unanswered
0
Accuracy
56.7%
Average
79.3%
Genetics
Correct
7
Incorrect
4
Unanswered
0
Accuracy
63.6%
Average
78.7%
Geriatrics
Correct
6
Incorrect
7
Unanswered
0
Accuracy
46.2%
Average
83.0%
Gynecology and Obstetrics
Correct
8
Incorrect
3
Unanswered
1
Accuracy
66.7%
Average
84.3%
Health Planning and Management
Correct
7
Incorrect
2
Unanswered
1
Accuracy
70.0%
Average
78.4%
Hematology
Correct
4
Incorrect
5
Unanswered
0
Accuracy
44.4%
Average
76.6%
Immunology
Correct
6
Incorrect
0
Unanswered
0
Accuracy
100.0%
Average
91.4%
Infectious Diseases
Correct
8
Incorrect
4
Unanswered
2
Accuracy
57.1%
Average
77.9%
Legal Medicine and Bioethics
Correct
9
Incorrect
1
Unanswered
1
Accuracy
81.8%
Average
82.9%
Medical Oncology
Correct
17
Incorrect
5
Unanswered
1
Accuracy
73.9%
Average
83.0%
Nephrology
Correct
7
Incorrect
3
Unanswered
0
Accuracy
70.0%
Average
85.1%
Neurology
Correct
9
Incorrect
4
Unanswered
0
Accuracy
69.2%
Average
88.6%
Ophthalmology
Correct
1
Incorrect
4
Unanswered
0
Accuracy
20.0%
Average
83.7%
Palliative Care
Correct
6
Incorrect
0
Unanswered
0
Accuracy
100.0%
Average
80.2%
Pediatrics
Correct
17
Incorrect
5
Unanswered
0
Accuracy
77.3%
Average
87.6%
Pharmacology
Correct
6
Incorrect
5
Unanswered
0
Accuracy
54.5%
Average
78.6%
Psychiatry
Correct
7
Incorrect
1
Unanswered
0
Accuracy
87.5%
Average
87.9%
Pulmonology
Correct
11
Incorrect
4
Unanswered
1
Accuracy
68.8%
Average
82.8%
Radiology-Emergency
Correct
8
Incorrect
5
Unanswered
0
Accuracy
61.5%
Average
67.7%
Rheumatology
Correct
10
Incorrect
1
Unanswered
0
Accuracy
90.9%
Average
88.4%
Statistics
Correct
2
Incorrect
0
Unanswered
0
Accuracy
100.0%
Average
83.8%
Traumatology
Correct
6
Incorrect
5
Unanswered
0
Accuracy
54.5%
Average
65.2%
Urology
Correct
8
Incorrect
0
Unanswered
0
Accuracy
100.0%
Average
82.5%

Question Type Breakdown

Anatomy
Correct
1
Incorrect
2
Unanswered
0
Accuracy
33.3%
Average
82.6%
Biostatistics
Correct
2
Incorrect
0
Unanswered
0
Accuracy
100.0%
Average
83.8%
Diagnosis
Correct
50
Incorrect
30
Unanswered
1
Accuracy
61.7%
Average
82.2%
Epidemiology
Correct
7
Incorrect
1
Unanswered
1
Accuracy
77.8%
Average
88.7%
Ethics
Correct
6
Incorrect
0
Unanswered
0
Accuracy
100.0%
Average
92.0%
Interpretation
Correct
22
Incorrect
14
Unanswered
1
Accuracy
59.5%
Average
72.0%
Legal
Correct
7
Incorrect
2
Unanswered
0
Accuracy
77.8%
Average
82.4%
Pathophysiology
Correct
20
Incorrect
6
Unanswered
0
Accuracy
76.9%
Average
84.3%
Pharmacology
Correct
10
Incorrect
5
Unanswered
0
Accuracy
66.7%
Average
82.3%
Prevention
Correct
12
Incorrect
2
Unanswered
2
Accuracy
75.0%
Average
80.6%
Prognosis
Correct
5
Incorrect
0
Unanswered
0
Accuracy
100.0%
Average
93.2%
Risk
Correct
12
Incorrect
2
Unanswered
1
Accuracy
80.0%
Average
84.3%
Tests
Correct
22
Incorrect
10
Unanswered
1
Accuracy
66.7%
Average
80.3%
Treatment
Correct
49
Incorrect
22
Unanswered
1
Accuracy
68.1%
Average
80.1%
#AnswerCorrectStatus
1AA
2BB
3AD
4BD
5CB
6CC
7CB
8CD
9DD
10AA
11CB
12A
13AAnnulled
14CC
15CA
16CC
17BC
18CD
19BB
20CB
21BB
22CC
23BB
24CA
25CC
26AA
27BB
28DD
29AA
30D
31CC
32CC
33BB
34B
35BC
36CD
37AD
38AA
39CC
40AA
41DD
42AA
43BB
44BB
45BB
46BB
47DD
48BC
49CC
50AAnnulled
51AA
52CC
53BC
54CC
55AA
56DA
57A
58CA
59BB
60BB
61CC
62BB
63BB
64AAnnulled
65CC
66DC
67CC
68AA
69BB
70BB
71BB
72BB
73BB
74AA
75CC
76CC
77DA
78AD
79AA
80DD
81BC
82DD
83CB
84AA
85DD
86AA
87BB
88BB
89BB
90CC
91AA
92CC
93DD
94BC
95CC
96AB
97BB
98BA
99BB
100AC
101CC
102AA
103CC
104CC
105CC
106CB
107DC
108AA
109DC
110BC
111CB
112AC
113BC
114DD
115BB
116DD
117CC
118BB
119DA
120AA
121BC
122BB
123BB
124BB
125CC
126AB
127CC
128BB
129CC
130CC
131BB
132BB
133CC
134BB
135CC
136BB
137CD
138BB
139AAnnulled
140DD
141CA
142AAnnulled
143AA
144BD
145CC
146DC
147BB
148CC
149AB
150AB
151BB
152CC
153CC
154DD
155BB
156BA
157DD
158BB
159BC
160AA
161CAnnulled
162AA
163CC
164CC
165CA
166AA
167DD
168CC
169CB
170BB
171BA
172AB
173DD
174CC
175BB
176BA
177CD
178BD
179BB
180BC
181BB
182CC
183DD
184DD
185BB
186DD
187DD
188CC
189CC
190DB
191DD
192DD
193AC
194CC
195DD
196AA
197DC
198DA
199AB
200DD
201CC
202AA
203AA
204BC
205BB
206CC
207AA
208Annulled
209BB
210CC