MedicalBenchmark
OpenAI: GPT-4 (older v0314) provider

GPT-4 (older v0314)

191

#191 of 319 models in the general ranking

Cumulative performance across 3 MIR exams

Net score

484.00 pts

Accuracy

84.8%

Correct / Incorrect

509 / 75

Total Cost

$23.20

Overall Performance

(vs. average)
Accuracy

84.8%

avg: 80.6%

Net score

484.00 pts

avg: 453.30 pts

Correct

509

avg: 483

Incorrect

75

avg: 90

Total Cost

$23.20

avg: $9.58

Average response time

12.6s

avg: 17.9s

Output Tokens

241K

avg: 1.3M

Reasoning Tokens

0

avg: 898K

Average confidence

96.7%

avg: 95.4%

Breakdown by Exam

MIR 2024
173
Correct
175
Incorrect
18
Accuracy
87.5%
Net score
169.00
MIR 2025
201
Correct
162
Incorrect
34
Accuracy
81.0%
Net score
150.66
MIR 2026
189
Correct
172
Incorrect
23
Accuracy
86.0%
Net score
164.33