MedicalBenchmark
Anthropic: Claude 3.5 Haiku provider

Claude 3.5 Haiku

240

#240 of 319 modelsMIR 2025

Net score

131.66 pts

Accuracy

74.0%

Correct / Incorrect

148 / 49

Total Cost

$0.40

Overall Performance

(vs. average)
Accuracy

74.0%

avg: 77.9%

Net score

131.66 pts

avg: 143.96 pts

Correct

148

avg: 156

Incorrect

49

avg: 35

Total Cost

$0.40

avg: $3.36

Average response time

7.2s

avg: 19.0s

Output Tokens

75K

avg: 430K

Reasoning Tokens

0

avg: 306K

Average confidence

98.2%

avg: 95.2%

Subject Breakdown

Allergology
Correct
4
Incorrect
0
Unanswered
0
Accuracy
100.0%
Average
87.9%
Anesthesiology and Resuscitation
Correct
5
Incorrect
1
Unanswered
0
Accuracy
83.3%
Average
82.3%
Cardiology
Correct
18
Incorrect
3
Unanswered
1
Accuracy
81.8%
Average
78.6%
Dermatology
Correct
9
Incorrect
2
Unanswered
1
Accuracy
75.0%
Average
69.4%
Endocrinology and Nutrition
Correct
14
Incorrect
2
Unanswered
0
Accuracy
87.5%
Average
83.5%
ENT
Correct
6
Incorrect
2
Unanswered
0
Accuracy
75.0%
Average
74.8%
Epidemiology
Correct
5
Incorrect
2
Unanswered
0
Accuracy
71.4%
Average
69.1%
Gastroenterology
Correct
15
Incorrect
6
Unanswered
0
Accuracy
71.4%
Average
74.1%
Genetics
Correct
3
Incorrect
3
Unanswered
0
Accuracy
50.0%
Average
69.5%
Geriatrics
Correct
9
Incorrect
2
Unanswered
0
Accuracy
81.8%
Average
77.5%
Gynecology and Obstetrics
Correct
18
Incorrect
1
Unanswered
0
Accuracy
94.7%
Average
86.7%
Health Planning and Management
Correct
2
Incorrect
0
Unanswered
0
Accuracy
100.0%
Average
82.6%
Hematology
Correct
7
Incorrect
4
Unanswered
0
Accuracy
63.6%
Average
82.7%
Immunology
Correct
6
Incorrect
3
Unanswered
0
Accuracy
66.7%
Average
83.3%
Infectious Diseases
Correct
17
Incorrect
7
Unanswered
3
Accuracy
63.0%
Average
74.9%
Legal Medicine and Bioethics
Correct
2
Incorrect
3
Unanswered
0
Accuracy
40.0%
Average
68.4%
Medical Oncology
Correct
23
Incorrect
2
Unanswered
0
Accuracy
92.0%
Average
87.2%
Nephrology
Correct
12
Incorrect
2
Unanswered
0
Accuracy
85.7%
Average
84.8%
Neurology
Correct
14
Incorrect
6
Unanswered
0
Accuracy
70.0%
Average
77.3%
Ophthalmology
Correct
4
Incorrect
1
Unanswered
0
Accuracy
80.0%
Average
74.2%
Palliative Care
Correct
4
Incorrect
0
Unanswered
0
Accuracy
100.0%
Average
78.6%
Pediatrics
Correct
17
Incorrect
9
Unanswered
0
Accuracy
65.4%
Average
71.9%
Pharmacology
Correct
12
Incorrect
4
Unanswered
1
Accuracy
70.6%
Average
74.1%
Psychiatry
Correct
7
Incorrect
1
Unanswered
0
Accuracy
87.5%
Average
83.0%
Pulmonology
Correct
9
Incorrect
4
Unanswered
1
Accuracy
64.3%
Average
80.4%
Radiology-Emergency
Correct
8
Incorrect
6
Unanswered
0
Accuracy
57.1%
Average
69.4%
Rheumatology
Correct
10
Incorrect
5
Unanswered
0
Accuracy
66.7%
Average
76.6%
Statistics
Correct
2
Incorrect
1
Unanswered
0
Accuracy
66.7%
Average
76.6%
Traumatology
Correct
12
Incorrect
6
Unanswered
0
Accuracy
66.7%
Average
79.3%
Urology
Correct
3
Incorrect
4
Unanswered
0
Accuracy
42.9%
Average
80.7%

Question Type Breakdown

Anatomy
Correct
4
Incorrect
3
Unanswered
0
Accuracy
57.1%
Average
78.6%
Biostatistics
Correct
3
Incorrect
1
Unanswered
0
Accuracy
75.0%
Average
79.8%
Diagnosis
Correct
68
Incorrect
18
Unanswered
2
Accuracy
77.3%
Average
79.9%
Epidemiology
Correct
5
Incorrect
0
Unanswered
0
Accuracy
100.0%
Average
76.7%
Ethics
Correct
1
Incorrect
2
Unanswered
0
Accuracy
33.3%
Average
74.1%
Interpretation
Correct
28
Incorrect
14
Unanswered
0
Accuracy
66.7%
Average
70.7%
Legal
Correct
1
Incorrect
3
Unanswered
0
Accuracy
25.0%
Average
64.6%
Pathophysiology
Correct
18
Incorrect
9
Unanswered
0
Accuracy
66.7%
Average
76.1%
Pharmacology
Correct
10
Incorrect
3
Unanswered
0
Accuracy
76.9%
Average
83.3%
Prevention
Correct
8
Incorrect
3
Unanswered
1
Accuracy
66.7%
Average
75.6%
Prognosis
Correct
5
Incorrect
2
Unanswered
0
Accuracy
71.4%
Average
80.8%
Risk
Correct
5
Incorrect
0
Unanswered
0
Accuracy
100.0%
Average
85.2%
Tests
Correct
19
Incorrect
8
Unanswered
0
Accuracy
70.4%
Average
77.9%
Treatment
Correct
61
Incorrect
17
Unanswered
3
Accuracy
75.3%
Average
77.3%
#AnswerCorrectStatus
1BB
2AA
3CC
4CB
5AA
6CC
7CC
8AA
9CA
10DD
11DD
12DD
13AB
14DD
15BAnnulled
16CB
17CB
18CA
19CC
20CA
21CB
22CD
23CC
24DD
25CC
26AAnnulled
27AC
28AAnnulled
29DD
30CB
31DD
32AA
33DD
34DD
35BB
36DD
37AC
38CC
39DD
40AA
41DD
42CC
43BB
44DD
45BD
46AA
47AA
48AA
49DD
50BB
51CC
52BB
53AD
54BB
55AA
56AAnnulled
57CC
58BB
59DD
60AA
61AA
62DD
63BB
64BD
65AA
66AA
67BB
68AB
69AB
70AA
71DD
72AA
73CD
74CC
75AA
76BB
77BB
78BB
79AC
80CC
81CC
82DD
83BB
84DD
85BC
86CC
87AA
88CD
89CB
90DA
91DB
92DC
93BB
94CC
95AA
96CC
97DD
98CC
99AA
100CC
101BB
102DD
103CA
104CC
105AA
106CC
107BB
108DD
109AB
110CC
111AA
112BC
113BB
114CD
115DD
116CC
117AA
118DD
119CC
120AB
121BD
122CC
123CC
124CC
125DD
126DD
127BB
128DD
129AA
130DD
131DD
132AA
133BB
134CC
135DB
136CC
137CA
138DD
139DD
140BB
141AA
142BA
143BB
144BB
145DD
146CC
147BB
148BA
149CA
150DD
151AA
152AA
153BB
154BB
155BB
156CC
157AA
158CC
159CC
160A
161AA
162DAnnulled
163DD
164C
165DA
166BB
167CC
168DD
169DB
170BB
171DC
172BA
173DA
174BB
175BB
176CC
177BC
178BA
179DD
180AA
181DB
182CC
183BB
184BB
185BB
186DAnnulled
187CC
188DD
189DD
190AA
191AB
192A
193CC
194AA
195AA
196AA
197BB
198BC
199DD
200CC
201AB
202AA
203DD
204DC
205BB
206CD
207AA
208BC
209CC
210DB