MedicalBenchmark
OpenAI: gpt-oss-120b provider

gpt-oss-120b

90

#90 of 319 models in the general ranking

Cumulative performance across 3 MIR exams

Net score

544.33 pts

Accuracy

93.0%

Correct / Incorrect

558 / 41

Total Cost

$0.26

Overall Performance

(vs. average)
Accuracy

93.0%

avg: 80.6%

Net score

544.33 pts

avg: 453.30 pts

Correct

558

avg: 483

Incorrect

41

avg: 90

Total Cost

$0.26

avg: $9.58

Average response time

10.7s

avg: 17.9s

Output Tokens

470K

avg: 1.3M

Reasoning Tokens

223K

avg: 898K

Average confidence

99.8%

avg: 95.4%

Breakdown by Exam

MIR 2024
118
Correct
185
Incorrect
15
Accuracy
92.5%
Net score
180.00
MIR 2025
57
Correct
186
Incorrect
14
Accuracy
93.0%
Net score
181.33
MIR 2026
104
Correct
187
Incorrect
12
Accuracy
93.5%
Net score
183.00