Llemma 7b
316
#316 of 319 models — MIR 2025
Net score
3.33 pts
Accuracy
8.5%
Correct / Incorrect
17 / 41
Total Cost
$0.64
Overall Performance
(vs. average)Accuracy
8.5%
avg: 77.9%
Net score
3.33 pts
avg: 143.96 pts
Correct
17
avg: 156
Incorrect
41
avg: 35
Total Cost
$0.64
avg: $3.36
Average response time
65.0s
avg: 19.0s
Output Tokens
446K
avg: 430K
Reasoning Tokens
0
avg: 306K
Average confidence
29.0%
avg: 95.2%
Subject Breakdown
| Subject | Correct | Incorrect | Unanswered | Accuracy | Average |
|---|---|---|---|---|---|
Allergology | 0 | 1 | 3 | 0.0% | 87.9% |
Anesthesiology and Resuscitation | 2 | 1 | 3 | 33.3% | 82.3% |
Cardiology | 0 | 3 | 19 | 0.0% | 78.6% |
Dermatology | 2 | 4 | 6 | 16.7% | 69.4% |
Endocrinology and Nutrition | 1 | 3 | 12 | 6.3% | 83.5% |
ENT | 1 | 1 | 6 | 12.5% | 74.8% |
Epidemiology | 1 | 1 | 5 | 14.3% | 69.1% |
Gastroenterology | 1 | 4 | 16 | 4.8% | 74.1% |
Genetics | 0 | 1 | 5 | 0.0% | 69.5% |
Geriatrics | 0 | 3 | 8 | 0.0% | 77.5% |
Gynecology and Obstetrics | 1 | 4 | 14 | 5.3% | 86.7% |
Health Planning and Management | 0 | 0 | 2 | 0.0% | 82.6% |
Hematology | 2 | 3 | 6 | 18.2% | 82.7% |
Immunology | 2 | 1 | 6 | 22.2% | 83.3% |
Infectious Diseases | 5 | 4 | 18 | 18.5% | 74.9% |
Legal Medicine and Bioethics | 2 | 0 | 3 | 40.0% | 68.4% |
Medical Oncology | 4 | 6 | 15 | 16.0% | 87.2% |
Nephrology | 0 | 3 | 11 | 0.0% | 84.8% |
Neurology | 0 | 4 | 16 | 0.0% | 77.3% |
Ophthalmology | 0 | 3 | 2 | 0.0% | 74.2% |
Palliative Care | 1 | 0 | 3 | 25.0% | 78.6% |
Pediatrics | 2 | 3 | 21 | 7.7% | 71.9% |
Pharmacology | 2 | 5 | 10 | 11.8% | 74.1% |
Psychiatry | 1 | 1 | 6 | 12.5% | 83.0% |
Pulmonology | 0 | 4 | 10 | 0.0% | 80.4% |
Radiology-Emergency | 0 | 3 | 11 | 0.0% | 69.4% |
Rheumatology | 1 | 5 | 9 | 6.7% | 76.6% |
Statistics | 0 | 1 | 2 | 0.0% | 76.6% |
Traumatology | 2 | 4 | 12 | 11.1% | 79.3% |
Urology | 0 | 3 | 4 | 0.0% | 80.7% |
Allergology
Correct
0
Incorrect
1
Unanswered
3
Accuracy
0.0%
Average
87.9%
Anesthesiology and Resuscitation
Correct
2
Incorrect
1
Unanswered
3
Accuracy
33.3%
Average
82.3%
Cardiology
Correct
0
Incorrect
3
Unanswered
19
Accuracy
0.0%
Average
78.6%
Dermatology
Correct
2
Incorrect
4
Unanswered
6
Accuracy
16.7%
Average
69.4%
Endocrinology and Nutrition
Correct
1
Incorrect
3
Unanswered
12
Accuracy
6.3%
Average
83.5%
ENT
Correct
1
Incorrect
1
Unanswered
6
Accuracy
12.5%
Average
74.8%
Epidemiology
Correct
1
Incorrect
1
Unanswered
5
Accuracy
14.3%
Average
69.1%
Gastroenterology
Correct
1
Incorrect
4
Unanswered
16
Accuracy
4.8%
Average
74.1%
Genetics
Correct
0
Incorrect
1
Unanswered
5
Accuracy
0.0%
Average
69.5%
Geriatrics
Correct
0
Incorrect
3
Unanswered
8
Accuracy
0.0%
Average
77.5%
Gynecology and Obstetrics
Correct
1
Incorrect
4
Unanswered
14
Accuracy
5.3%
Average
86.7%
Health Planning and Management
Correct
0
Incorrect
0
Unanswered
2
Accuracy
0.0%
Average
82.6%
Hematology
Correct
2
Incorrect
3
Unanswered
6
Accuracy
18.2%
Average
82.7%
Immunology
Correct
2
Incorrect
1
Unanswered
6
Accuracy
22.2%
Average
83.3%
Infectious Diseases
Correct
5
Incorrect
4
Unanswered
18
Accuracy
18.5%
Average
74.9%
Legal Medicine and Bioethics
Correct
2
Incorrect
0
Unanswered
3
Accuracy
40.0%
Average
68.4%
Medical Oncology
Correct
4
Incorrect
6
Unanswered
15
Accuracy
16.0%
Average
87.2%
Nephrology
Correct
0
Incorrect
3
Unanswered
11
Accuracy
0.0%
Average
84.8%
Neurology
Correct
0
Incorrect
4
Unanswered
16
Accuracy
0.0%
Average
77.3%
Ophthalmology
Correct
0
Incorrect
3
Unanswered
2
Accuracy
0.0%
Average
74.2%
Palliative Care
Correct
1
Incorrect
0
Unanswered
3
Accuracy
25.0%
Average
78.6%
Pediatrics
Correct
2
Incorrect
3
Unanswered
21
Accuracy
7.7%
Average
71.9%
Pharmacology
Correct
2
Incorrect
5
Unanswered
10
Accuracy
11.8%
Average
74.1%
Psychiatry
Correct
1
Incorrect
1
Unanswered
6
Accuracy
12.5%
Average
83.0%
Pulmonology
Correct
0
Incorrect
4
Unanswered
10
Accuracy
0.0%
Average
80.4%
Radiology-Emergency
Correct
0
Incorrect
3
Unanswered
11
Accuracy
0.0%
Average
69.4%
Rheumatology
Correct
1
Incorrect
5
Unanswered
9
Accuracy
6.7%
Average
76.6%
Statistics
Correct
0
Incorrect
1
Unanswered
2
Accuracy
0.0%
Average
76.6%
Traumatology
Correct
2
Incorrect
4
Unanswered
12
Accuracy
11.1%
Average
79.3%
Urology
Correct
0
Incorrect
3
Unanswered
4
Accuracy
0.0%
Average
80.7%
Question Type Breakdown
| Type | Correct | Incorrect | Unanswered | Accuracy | Average |
|---|---|---|---|---|---|
Anatomy | 0 | 1 | 6 | 0.0% | 78.6% |
Biostatistics | 0 | 1 | 3 | 0.0% | 79.8% |
Diagnosis | 7 | 18 | 63 | 8.0% | 79.9% |
Epidemiology | 1 | 0 | 4 | 20.0% | 76.7% |
Ethics | 0 | 0 | 3 | 0.0% | 74.1% |
Interpretation | 2 | 7 | 33 | 4.8% | 70.7% |
Legal | 2 | 0 | 2 | 50.0% | 64.6% |
Pathophysiology | 2 | 6 | 19 | 7.4% | 76.1% |
Pharmacology | 1 | 5 | 7 | 7.7% | 83.3% |
Prevention | 2 | 2 | 8 | 16.7% | 75.6% |
Prognosis | 1 | 1 | 5 | 14.3% | 80.8% |
Risk | 0 | 1 | 4 | 0.0% | 85.2% |
Tests | 1 | 5 | 21 | 3.7% | 77.9% |
Treatment | 6 | 19 | 56 | 7.4% | 77.3% |
Anatomy
Correct
0
Incorrect
1
Unanswered
6
Accuracy
0.0%
Average
78.6%
Biostatistics
Correct
0
Incorrect
1
Unanswered
3
Accuracy
0.0%
Average
79.8%
Diagnosis
Correct
7
Incorrect
18
Unanswered
63
Accuracy
8.0%
Average
79.9%
Epidemiology
Correct
1
Incorrect
0
Unanswered
4
Accuracy
20.0%
Average
76.7%
Ethics
Correct
0
Incorrect
0
Unanswered
3
Accuracy
0.0%
Average
74.1%
Interpretation
Correct
2
Incorrect
7
Unanswered
33
Accuracy
4.8%
Average
70.7%
Legal
Correct
2
Incorrect
0
Unanswered
2
Accuracy
50.0%
Average
64.6%
Pathophysiology
Correct
2
Incorrect
6
Unanswered
19
Accuracy
7.4%
Average
76.1%
Pharmacology
Correct
1
Incorrect
5
Unanswered
7
Accuracy
7.7%
Average
83.3%
Prevention
Correct
2
Incorrect
2
Unanswered
8
Accuracy
16.7%
Average
75.6%
Prognosis
Correct
1
Incorrect
1
Unanswered
5
Accuracy
14.3%
Average
80.8%
Risk
Correct
0
Incorrect
1
Unanswered
4
Accuracy
0.0%
Average
85.2%
Tests
Correct
1
Incorrect
5
Unanswered
21
Accuracy
3.7%
Average
77.9%
Treatment
Correct
6
Incorrect
19
Unanswered
56
Accuracy
7.4%
Average
77.3%