MedicalBenchmark
OpenAI: GPT-4.1 provider

GPT-4.1

67

#67 of 319 models in the general ranking

Cumulative performance across 3 MIR exams

Net score

555.00 pts

Accuracy

94.3%

Correct / Incorrect

566 / 33

Total Cost

$2.75

Overall Performance

(vs. average)
Accuracy

94.3%

avg: 80.6%

Net score

555.00 pts

avg: 453.30 pts

Correct

566

avg: 483

Incorrect

33

avg: 90

Total Cost

$2.75

avg: $9.58

Average response time

8.8s

avg: 17.9s

Output Tokens

270K

avg: 1.3M

Reasoning Tokens

0

avg: 898K

Average confidence

99.8%

avg: 95.4%

Breakdown by Exam

MIR 2024
43
Correct
192
Incorrect
8
Accuracy
96.0%
Net score
189.33
MIR 2025
96
Correct
180
Incorrect
19
Accuracy
90.0%
Net score
173.66
MIR 2026
48
Correct
194
Incorrect
6
Accuracy
97.0%
Net score
192.00