MedicalBenchmark
OpenAI: GPT-5.1 Chat provider

GPT-5.1 Chat

7

#7 of 319 models in the general ranking

Cumulative performance across 3 MIR exams

Net score

580.00 pts

Accuracy

97.5%

Correct / Incorrect

585 / 15

Total Cost

$2.07

Overall Performance

(vs. average)
Accuracy

97.5%

avg: 80.6%

Net score

580.00 pts

avg: 453.30 pts

Correct

585

avg: 483

Incorrect

15

avg: 90

Total Cost

$2.07

avg: $9.58

Average response time

3.8s

avg: 17.9s

Output Tokens

171K

avg: 1.3M

Reasoning Tokens

24K

avg: 898K

Average confidence

99.8%

avg: 95.4%

Breakdown by Exam

MIR 2024
18
Correct
194
Incorrect
6
Accuracy
97.0%
Net score
192.00
MIR 2025
14
Correct
193
Incorrect
7
Accuracy
96.5%
Net score
190.66
MIR 2026
7
Correct
198
Incorrect
2
Accuracy
99.0%
Net score
197.33