MedicalBenchmark
xAI: Grok 3 provider

Grok 3

69

#69 of 319 models in the general ranking

Cumulative performance across 3 MIR exams

Net score

554.66 pts

Accuracy

94.2%

Correct / Incorrect

565 / 31

Total Cost

$7.98

Overall Performance

(vs. average)
Accuracy

94.2%

avg: 80.6%

Net score

554.66 pts

avg: 453.30 pts

Correct

565

avg: 483

Incorrect

31

avg: 90

Total Cost

$7.98

avg: $9.58

Average response time

15.9s

avg: 17.9s

Output Tokens

499K

avg: 1.3M

Reasoning Tokens

0

avg: 898K

Average confidence

98.2%

avg: 95.4%

Breakdown by Exam

MIR 2024
32
Correct
193
Incorrect
7
Accuracy
96.5%
Net score
190.66
MIR 2025
87
Correct
181
Incorrect
17
Accuracy
90.5%
Net score
175.33
MIR 2026
66
Correct
191
Incorrect
7
Accuracy
95.5%
Net score
188.66