MedicalBenchmark
Anthropic: Claude 3.5 Sonnet provider

Claude 3.5 Sonnet

73

#73 of 319 models in the general ranking

Cumulative performance across 3 MIR exams

Net score

552.66 pts

Accuracy

94.0%

Correct / Incorrect

564 / 34

Total Cost

$9.99

Overall Performance

(vs. average)
Accuracy

94.0%

avg: 80.6%

Net score

552.66 pts

avg: 453.30 pts

Correct

564

avg: 483

Incorrect

34

avg: 90

Total Cost

$9.99

avg: $9.58

Average response time

11.1s

avg: 17.9s

Output Tokens

261K

avg: 1.3M

Reasoning Tokens

0

avg: 898K

Average confidence

99.4%

avg: 95.4%

Breakdown by Exam

MIR 2024
23
Correct
194
Incorrect
6
Accuracy
97.0%
Net score
192.00
MIR 2025
78
Correct
182
Incorrect
17
Accuracy
91.0%
Net score
176.33
MIR 2026
99
Correct
188
Incorrect
11
Accuracy
94.0%
Net score
184.33