MedicalBenchmark
Sao10K: Llama 3.3 Euryale 70B provider

Llama 3.3 Euryale 70B

209

#209 of 319 models in the general ranking

Cumulative performance across 3 MIR exams

Net score

465.00 pts

Accuracy

81.7%

Correct / Incorrect

490 / 75

Total Cost

$0.50

Overall Performance

(vs. average)
Accuracy

81.7%

avg: 80.6%

Net score

465.00 pts

avg: 453.30 pts

Correct

490

avg: 483

Incorrect

75

avg: 90

Total Cost

$0.50

avg: $9.58

Average response time

19.7s

avg: 17.9s

Output Tokens

365K

avg: 1.3M

Reasoning Tokens

0

avg: 898K

Average confidence

92.5%

avg: 95.4%

Breakdown by Exam

MIR 2024
212
Correct
165
Incorrect
26
Accuracy
82.5%
Net score
156.33
MIR 2025
217
Correct
154
Incorrect
33
Accuracy
77.0%
Net score
143.00
MIR 2026
182
Correct
171
Incorrect
16
Accuracy
85.5%
Net score
165.66