MedicalBenchmark
OpenAI: GPT-3.5 Turbo 16k provider

GPT-3.5 Turbo 16k

268

#268 of 319 models in the general ranking

Cumulative performance across 3 MIR exams

Net score

303.66 pts

Accuracy

62.5%

Correct / Incorrect

375 / 214

Total Cost

$0.00

Overall Performance

(vs. average)
Accuracy

62.5%

avg: 80.6%

Net score

303.66 pts

avg: 453.30 pts

Correct

375

avg: 483

Incorrect

214

avg: 90

Total Cost

$0.00

avg: $9.58

Average response time

2.6s

avg: 17.9s

Output Tokens

182K

avg: 1.3M

Reasoning Tokens

0

avg: 898K

Average confidence

97.6%

avg: 95.4%

Breakdown by Exam

MIR 2024
280
Correct
116
Incorrect
83
Accuracy
58.0%
Net score
88.33
MIR 2025
267
Correct
121
Incorrect
75
Accuracy
60.5%
Net score
96.00
MIR 2026
262
Correct
138
Incorrect
56
Accuracy
69.0%
Net score
119.33