MedicalBenchmark
Anthropic: Claude 3.7 Sonnet provider

Claude 3.7 Sonnet

61

#61 of 319 models in the general ranking

Cumulative performance across 3 MIR exams

Net score

557.66 pts

Accuracy

94.5%

Correct / Incorrect

567 / 28

Total Cost

$7.46

Overall Performance

(vs. average)
Accuracy

94.5%

avg: 80.6%

Net score

557.66 pts

avg: 453.30 pts

Correct

567

avg: 483

Incorrect

28

avg: 90

Total Cost

$7.46

avg: $9.58

Average response time

10.3s

avg: 17.9s

Output Tokens

425K

avg: 1.3M

Reasoning Tokens

0

avg: 898K

Average confidence

99.1%

avg: 95.4%

Breakdown by Exam

MIR 2024
63
Correct
191
Incorrect
9
Accuracy
95.5%
Net score
188.00
MIR 2025
61
Correct
185
Incorrect
11
Accuracy
92.5%
Net score
181.33
MIR 2026
70
Correct
191
Incorrect
8
Accuracy
95.5%
Net score
188.33