MedicalBenchmark
Anthropic: Claude Opus 4.1 provider

Claude Opus 4.1

65

#65 of 319 models in the general ranking

Cumulative performance across 3 MIR exams

Net score

556.33 pts

Accuracy

94.5%

Correct / Incorrect

567 / 32

Total Cost

$33.53

Overall Performance

(vs. average)
Accuracy

94.5%

avg: 80.6%

Net score

556.33 pts

avg: 453.30 pts

Correct

567

avg: 483

Incorrect

32

avg: 90

Total Cost

$33.53

avg: $9.58

Average response time

30.2s

avg: 17.9s

Output Tokens

375K

avg: 1.3M

Reasoning Tokens

0

avg: 898K

Average confidence

99.8%

avg: 95.4%

Breakdown by Exam

MIR 2024
91
Correct
189
Incorrect
11
Accuracy
94.5%
Net score
185.33
MIR 2025
89
Correct
181
Incorrect
18
Accuracy
90.5%
Net score
175.00
MIR 2026
25
Correct
197
Incorrect
3
Accuracy
98.5%
Net score
196.00