MedicalBenchmark
OpenAI: GPT-5.1-Codex provider

GPT-5.1-Codex

28

#28 of 319 models in the general ranking

Cumulative performance across 3 MIR exams

Net score

573.33 pts

Accuracy

96.7%

Correct / Incorrect

580 / 20

Total Cost

$1.96

Overall Performance

(vs. average)
Accuracy

96.7%

avg: 80.6%

Net score

573.33 pts

avg: 453.30 pts

Correct

580

avg: 483

Incorrect

20

avg: 90

Total Cost

$1.96

avg: $9.58

Average response time

3.4s

avg: 17.9s

Output Tokens

160K

avg: 1.3M

Reasoning Tokens

64K

avg: 898K

Average confidence

99.4%

avg: 95.4%

Breakdown by Exam

MIR 2024
42
Correct
192
Incorrect
8
Accuracy
96.0%
Net score
189.33
MIR 2025
21
Correct
192
Incorrect
8
Accuracy
96.0%
Net score
189.33
MIR 2026
30
Correct
196
Incorrect
4
Accuracy
98.0%
Net score
194.66