MedicalBenchmark
OpenAI: o4 Mini Deep Research provider

o4 Mini Deep Research

38

#38 of 319 models in the general ranking

Cumulative performance across 3 MIR exams

Net score

568.00 pts

Accuracy

96.0%

Correct / Incorrect

576 / 24

Total Cost

$107.19

Overall Performance

(vs. average)
Accuracy

96.0%

avg: 80.6%

Net score

568.00 pts

avg: 453.30 pts

Correct

576

avg: 483

Incorrect

24

avg: 90

Total Cost

$107.19

avg: $9.58

Average response time

94.6s

avg: 17.9s

Output Tokens

4.9M

avg: 1.3M

Reasoning Tokens

4.6M

avg: 898K

Average confidence

100.0%

avg: 95.4%

Breakdown by Exam

MIR 2024
78
Correct
190
Incorrect
10
Accuracy
95.0%
Net score
186.66
MIR 2025
33
Correct
190
Incorrect
10
Accuracy
95.0%
Net score
186.66
MIR 2026
32
Correct
196
Incorrect
4
Accuracy
98.0%
Net score
194.66