MedicalBenchmark
OpenAI: GPT-4o-mini provider

GPT-4o-mini

221

#221 of 319 models in the general ranking

Cumulative performance across 3 MIR exams

Net score

450.33 pts

Accuracy

81.0%

Correct / Incorrect

486 / 107

Total Cost

$0.32

Overall Performance

(vs. average)
Accuracy

81.0%

avg: 80.6%

Net score

450.33 pts

avg: 453.30 pts

Correct

486

avg: 483

Incorrect

107

avg: 90

Total Cost

$0.32

avg: $9.58

Average response time

6.6s

avg: 17.9s

Output Tokens

221K

avg: 1.3M

Reasoning Tokens

0

avg: 898K

Average confidence

98.6%

avg: 95.4%

Breakdown by Exam

MIR 2024
211
Correct
167
Incorrect
29
Accuracy
83.5%
Net score
157.33
MIR 2025
218
Correct
157
Incorrect
43
Accuracy
78.5%
Net score
142.66
MIR 2026
235
Correct
162
Incorrect
35
Accuracy
81.0%
Net score
150.33