MedicalBenchmark
xAI: Grok 4 provider

Grok 4

43

#43 of 319 models in the general ranking

Cumulative performance across 3 MIR exams

Net score

565.00 pts

Accuracy

95.5%

Correct / Incorrect

573 / 24

Total Cost

$13.62

Overall Performance

(vs. average)
Accuracy

95.5%

avg: 80.6%

Net score

565.00 pts

avg: 453.30 pts

Correct

573

avg: 483

Incorrect

24

avg: 90

Total Cost

$13.62

avg: $9.58

Average response time

32.0s

avg: 17.9s

Output Tokens

841K

avg: 1.3M

Reasoning Tokens

522K

avg: 898K

Average confidence

99.4%

avg: 95.4%

Breakdown by Exam

MIR 2024
50
Correct
192
Incorrect
8
Accuracy
96.0%
Net score
189.33
MIR 2025
49
Correct
187
Incorrect
12
Accuracy
93.5%
Net score
183.00
MIR 2026
41
Correct
194
Incorrect
4
Accuracy
97.0%
Net score
192.66