Benchmarks

Real-world deployments of sovereign AI infrastructure in enterprise environments.

Our Expert AI Models are designed for unmatched accuracy, speed, and security in an Enterprise environment.

Get started

Model Performance

View model performance and system benchmarks

Summary
Data Table
Model Strengths

Us Inc - Model Performance - MMLU

Model
US Inc
USF-1 Mini
90%
Model
Gemini 2.0 Flash
87%
Model
DeepSeek V3
86%
Model
GPT 4o (Nov-24)
86%
Model
US Inc
USF Alpha
85%
Model
LLAMA 3.1 405B
85%
Model
O1 Mini
85%
Model
LLAMA 3.3 70B
84%
Model
GPT 4o Mini
82%

Model Performance Comparison

MMLU Score (%)
US Inc Models
Other Models
USF Mini
90%
Gemini 2.0 Flash
87%
Deepseek V3
86%
GPT 4o (Nov-24)
86%
USF Alpha
85%
LLAMA 3.1405B
85%
O1 Mini
85%
LLAMA 3.3 70B
84%
GPT 4o Mini
82%
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
#
Task
USF-1 Mini
Gemini 2.0 Flash
DeepSeek V3
GPT 4o (Nov-24)
USF Alpha
LLAMA 3.1 405B
O1 Mini
LLAMA 3.3 70B
GPT 4o Mini
Average
90%
87%
86%
86%
85%
85%
85%
84%
84%
1
High School European History
Humanities
88
89
87
91
88
86
85
85
85
2
Business Ethics
Professional
88
77
78
85
86
83
82
81
75
3
Clinical Knowledge
89
88
91
89
89
88
85
87
87
4
Medical Genetics
Science
98
96
96
97
90
94
96
95
92
5
High School US History
Humanities
95
95
96
95
92
94
90
94
90
6
High School Physics
Science
91
89
80
89
77
77
88
78
77
7
High School World History
Humanities
92
91
93
93
92
94
85
93
89
8
Virology
Science
55
55
60
55
60
57
59
57
54
9
High School Microeconomics
Social Sciences
97
95
95
97
98
95
94
95
93
10
Econometrics
85
81
73
73
75
74
77
70
66
11
College Computer Science
Computer Science
98
89
79
85
83
85
93
79
75
12
High School Biology
Science
95
95
94
95
95
93
94
94
91
13
Abstract Algebra
95
82
80
65
81
75
90
72
67
14
Professional Accounting
Professional
88
76
80
92
78
77
85
82
78
15
Philosophy
Humanities
86
89
90
87
86
87
77
83
79
16
Professional Medicine
Professional
94
90
94
94
91
91
94
94
90
17
Nutrition
90
87
91
88
89
92
86
89
84
18
Global Facts
61
58
69
62
55
69
63
68
51
19
Machine Learning
Computer Science
90
82
80
76
79
77
83
76
67
20
Security Studies
Computer Science
81
80
82
80
85
84
81
83
76
21
Public Relations
75
78
76
81
80
78
72
76
75
22
Professional Psychology
Social Sciences
86
88
88
87
86
87
82
85
83
23
Prehistory
Humanities
91
93
92
91
90
91
84
88
84
24
Anatomy
Science
83
83
86
88
85
82
83
83
81
25
Human Sexuality
91
93
92
92
82
89
82
89
88
26
College Medicine
86
84
84
83
84
78
84
82
81
27
High School Government and Politics
Social Sciences
96
99
98
97
99
96
95
98
95
28
College Chemistry
Science
74
73
62
61
67
68
73
66
60
29
Logical Fallacies
91
90
90
88
87
90
86
85
86
30
High School Geography
92
94
95
95
93
95
90
94
94
31
Elementary Mathematics
Mathematics
98
95
96
97
96
93
97
89
94
32
Human Aging
80
80
84
82
87
84
77
83
81
33
College Mathematics
Mathematics
97
88
78
70
64
65
92
76
71
34
High School Psychology
Social Sciences
96
95
96
96
95
95
94
96
93
35
Formal Logic
98
83
72
78
75
74
93
66
61
36
High School Statistics
Mathematics
94
89
85
86
85
87
90
84
80
37
International Law
Professional
92
86
94
93
90
94
85
88
90
38
High School Mathematics
Mathematics
99
95
75
89
64
76
97
76
84
39
High School Computer Science
Computer Science
95
91
95
92
91
93
97
94
91
40
Conceptual Physics
Science
93
92
95
91
94
88
91
85
82
41
Miscellaneous
95
95
95
95
95
95
91
95
91
42
High School Chemistry
Science
93
91
85
86
81
81
92
81
79
43
Marketing
Professional
93
95
94
92
95
95
93
94
94
44
Professional Law
Professional
73
66
69
73
69
69
56
65
54
45
Management
Professional
90
91
92
92
91
90
84
89
87
46
College Physics
Science
95
95
86
90
82
75
94
84
84
47
Jurisprudence
90
90
89
91
90
91
79
87
84
48
World Religions
Humanities
92
88
91
87
89
90
85
89
87
49
Sociology
Social Sciences
89
90
94
92
92
95
89
92
91
50
US Foreign Policy
Social Sciences
93
95
93
96
93
94
87
92
90
51
High School Macroeconomics
Social Sciences
93
92
91
88
91
92
92
89
89
52
Computer Security
Computer Science
92
86
82
77
89
82
84
87
85
53
Moral Scenarios
76
66
79
82
81
88
70
78
61
54
Moral Disputes
83
86
86
87
86
86
74
85
82
55
Electrical Engineering
Computer Science
90
86
86
83
87
81
80
81
79
56
Astronomy
Science
97
93
94
95
92
94
93
92
93
57
College Biology
97
95
95
96
96
95
95
94
94
No items found
Your search did not find any items.
Please try again.
Reset All

USF-1 MINI

Model 1 of 9
Swipe left/right to change models
Average
90%
#
Task
Score
1
High School European History
88
2
Business Ethics
88
3
Clinical Knowledge
89
4
Medical Genetics
98
5
High School Us History
95
6
High School Physics
91
7
High School World History
92
8
Virology
55
9
High School Microeconomics
97
10
Econometrics
85
11
College Computer Science
98
12
High School Biology
95
13
Abstract Algebra
95
14
Professional Accounting
88
15
Philosophy
86
16
Professional Medicine
94
17
Nutrition
90
18
Global Facts
61
19
Machine Learning
90
20
Security Studies
81
21
Public Relations
75
22
Professional Psychology
86
23
Prehistory
91
24
Anatomy
83
25
Human Sexuality
91
26
College Medicine
86
27
High School Government And Politics
96
28
College Chemistry
74
29
Logical Fallacies
91
30
High School Geography
92
31
Elementary Mathematics
98
32
Human Aging
80
33
College Mathematics
97
34
High School Psychology
96
35
Formal Logic
98
36
High School Statistics
94
37
International Law
92
38
High School Mathematics
99
39
High School Computer Science
95
40
Conceptual Physics
93
41
Miscellaneous
95
42
High School Chemistry
93
43
Marketing
93
44
Professional Law
73
45
Management
90
46
College Physics
95
47
Jurisprudence
90
48
World Religions
92
49
Sociology
89
50
Us Foreign Policy
93
51
High School Macroeconomics
93
52
Computer Security
92
53
Moral Scenarios
76
54
Moral Disputes
83
55
Electrical Engineering
90
56
Astronomy
97
57
College Biology
97

Gemini 2.0 Flash

Model 2 of 9
Swipe left/right to change models
Average
87%
#
Task
Score
1
High School European History
89
2
Business Ethics
77
3
Clinical Knowledge
88
4
Medical Genetics
96
5
High School Us History
95
6
High School Physics
89
7
High School World History
91
8
Virology
55
9
High School Microeconomics
95
10
Econometrics
81
11
College Computer Science
89
12
High School Biology
95
13
Abstract Algebra
82
14
Professional Accounting
76
15
Philosophy
89
16
Professional Medicine
90
17
Nutrition
87
18
Global Facts
58
19
Machine Learning
82
20
Security Studies
80
21
Public Relations
78
22
Professional Psychology
88
23
Prehistory
93
24
Anatomy
83
25
Human Sexuality
93
26
College Medicine
84
27
High School Government And Politics
99
28
College Chemistry
73
29
Logical Fallacies
90
30
High School Geography
94
31
Elementary Mathematics
95
32
Human Aging
80
33
College Mathematics
88
34
High School Psychology
95
35
Formal Logic
83
36
High School Statistics
89
37
International Law
86
38
High School Mathematics
95
39
High School Computer Science
91
40
Conceptual Physics
92
41
Miscellaneous
95
42
High School Chemistry
91
43
Marketing
95
44
Professional Law
66
45
Management
91
46
College Physics
95
47
Jurisprudence
90
48
World Religions
88
49
Sociology
90
50
Us Foreign Policy
95
51
High School Macroeconomics
92
52
Computer Security
86
53
Moral Scenarios
66
54
Moral Disputes
86
55
Electrical Engineering
86
56
Astronomy
93
57
College Biology
95

DeepSeek V3

Model 3 of 9
Swipe left/right to change models
Average
86%
#
Task
Score
1
High School European History
87
2
Business Ethics
78
3
Clinical Knowledge
91
4
Medical Genetics
96
5
High School Us History
96
6
High School Physics
80
7
High School World History
93
8
Virology
60
9
High School Microeconomics
95
10
Econometrics
73
11
College Computer Science
79
12
High School Biology
94
13
Abstract Algebra
80
14
Professional Accounting
80
15
Philosophy
90
16
Professional Medicine
94
17
Nutrition
91
18
Global Facts
69
19
Machine Learning
80
20
Security Studies
82
21
Public Relations
76
22
Professional Psychology
88
23
Prehistory
92
24
Anatomy
86
25
Human Sexuality
92
26
College Medicine
84
27
High School Government And Politics
98
28
College Chemistry
62
29
Logical Fallacies
90
30
High School Geography
95
31
Elementary Mathematics
96
32
Human Aging
84
33
College Mathematics
78
34
High School Psychology
96
35
Formal Logic
72
36
High School Statistics
85
37
International Law
94
38
High School Mathematics
75
39
High School Computer Science
95
40
Conceptual Physics
95
41
Miscellaneous
95
42
High School Chemistry
85
43
Marketing
94
44
Professional Law
69
45
Management
92
46
College Physics
86
47
Jurisprudence
89
48
World Religions
91
49
Sociology
94
50
Us Foreign Policy
93
51
High School Macroeconomics
91
52
Computer Security
82
53
Moral Scenarios
79
54
Moral Disputes
86
55
Electrical Engineering
86
56
Astronomy
94
57
College Biology
95

GPT 4o (Nov-24)

Model 4 of 9
Swipe left/right to change models
Average
86%
#
Task
Score
1
High School European History
91
2
Business Ethics
85
3
Clinical Knowledge
89
4
Medical Genetics
97
5
High School Us History
95
6
High School Physics
89
7
High School World History
93
8
Virology
55
9
High School Microeconomics
97
10
Econometrics
73
11
College Computer Science
85
12
High School Biology
95
13
Abstract Algebra
65
14
Professional Accounting
92
15
Philosophy
87
16
Professional Medicine
94
17
Nutrition
88
18
Global Facts
62
19
Machine Learning
76
20
Security Studies
80
21
Public Relations
81
22
Professional Psychology
87
23
Prehistory
91
24
Anatomy
88
25
Human Sexuality
92
26
College Medicine
83
27
High School Government And Politics
97
28
College Chemistry
61
29
Logical Fallacies
88
30
High School Geography
95
31
Elementary Mathematics
97
32
Human Aging
82
33
College Mathematics
70
34
High School Psychology
96
35
Formal Logic
78
36
High School Statistics
86
37
International Law
93
38
High School Mathematics
89
39
High School Computer Science
92
40
Conceptual Physics
91
41
Miscellaneous
95
42
High School Chemistry
86
43
Marketing
92
44
Professional Law
73
45
Management
92
46
College Physics
90
47
Jurisprudence
91
48
World Religions
87
49
Sociology
92
50
Us Foreign Policy
96
51
High School Macroeconomics
88
52
Computer Security
77
53
Moral Scenarios
82
54
Moral Disputes
87
55
Electrical Engineering
83
56
Astronomy
95
57
College Biology
96

USF Alpha

Model 5 of 9
Swipe left/right to change models
Average
85%
#
Task
Score
1
High School European History
88
2
Business Ethics
86
3
Clinical Knowledge
89
4
Medical Genetics
90
5
High School Us History
92
6
High School Physics
77
7
High School World History
92
8
Virology
60
9
High School Microeconomics
98
10
Econometrics
75
11
College Computer Science
83
12
High School Biology
95
13
Abstract Algebra
81
14
Professional Accounting
78
15
Philosophy
86
16
Professional Medicine
91
17
Nutrition
89
18
Global Facts
55
19
Machine Learning
79
20
Security Studies
85
21
Public Relations
80
22
Professional Psychology
86
23
Prehistory
90
24
Anatomy
85
25
Human Sexuality
82
26
College Medicine
84
27
High School Government And Politics
99
28
College Chemistry
67
29
Logical Fallacies
87
30
High School Geography
93
31
Elementary Mathematics
96
32
Human Aging
87
33
College Mathematics
64
34
High School Psychology
95
35
Formal Logic
75
36
High School Statistics
85
37
International Law
90
38
High School Mathematics
64
39
High School Computer Science
91
40
Conceptual Physics
94
41
Miscellaneous
95
42
High School Chemistry
81
43
Marketing
95
44
Professional Law
69
45
Management
91
46
College Physics
82
47
Jurisprudence
90
48
World Religions
89
49
Sociology
92
50
Us Foreign Policy
93
51
High School Macroeconomics
91
52
Computer Security
89
53
Moral Scenarios
81
54
Moral Disputes
86
55
Electrical Engineering
87
56
Astronomy
92
57
College Biology
96

LLAMA 3.1 405B

Model 6 of 9
Swipe left/right to change models
Average
85%
#
Task
Score
1
High School European History
86
2
Business Ethics
83
3
Clinical Knowledge
88
4
Medical Genetics
94
5
High School Us History
94
6
High School Physics
77
7
High School World History
94
8
Virology
57
9
High School Microeconomics
95
10
Econometrics
74
11
College Computer Science
85
12
High School Biology
93
13
Abstract Algebra
75
14
Professional Accounting
77
15
Philosophy
87
16
Professional Medicine
91
17
Nutrition
92
18
Global Facts
69
19
Machine Learning
77
20
Security Studies
84
21
Public Relations
78
22
Professional Psychology
87
23
Prehistory
91
24
Anatomy
82
25
Human Sexuality
89
26
College Medicine
78
27
High School Government And Politics
96
28
College Chemistry
68
29
Logical Fallacies
90
30
High School Geography
95
31
Elementary Mathematics
93
32
Human Aging
84
33
College Mathematics
65
34
High School Psychology
95
35
Formal Logic
74
36
High School Statistics
87
37
International Law
94
38
High School Mathematics
76
39
High School Computer Science
93
40
Conceptual Physics
88
41
Miscellaneous
95
42
High School Chemistry
81
43
Marketing
95
44
Professional Law
69
45
Management
90
46
College Physics
75
47
Jurisprudence
91
48
World Religions
90
49
Sociology
95
50
Us Foreign Policy
94
51
High School Macroeconomics
92
52
Computer Security
82
53
Moral Scenarios
88
54
Moral Disputes
86
55
Electrical Engineering
81
56
Astronomy
94
57
College Biology
95

O1 Mini

Model 7 of 9
Swipe left/right to change models
Average
85%
#
Task
Score
1
High School European History
85
2
Business Ethics
82
3
Clinical Knowledge
85
4
Medical Genetics
96
5
High School Us History
90
6
High School Physics
88
7
High School World History
85
8
Virology
59
9
High School Microeconomics
94
10
Econometrics
77
11
College Computer Science
93
12
High School Biology
94
13
Abstract Algebra
90
14
Professional Accounting
85
15
Philosophy
77
16
Professional Medicine
94
17
Nutrition
86
18
Global Facts
63
19
Machine Learning
83
20
Security Studies
81
21
Public Relations
72
22
Professional Psychology
82
23
Prehistory
84
24
Anatomy
83
25
Human Sexuality
82
26
College Medicine
84
27
High School Government And Politics
95
28
College Chemistry
73
29
Logical Fallacies
86
30
High School Geography
90
31
Elementary Mathematics
97
32
Human Aging
77
33
College Mathematics
92
34
High School Psychology
94
35
Formal Logic
93
36
High School Statistics
90
37
International Law
85
38
High School Mathematics
97
39
High School Computer Science
97
40
Conceptual Physics
91
41
Miscellaneous
91
42
High School Chemistry
92
43
Marketing
93
44
Professional Law
56
45
Management
84
46
College Physics
94
47
Jurisprudence
79
48
World Religions
85
49
Sociology
89
50
Us Foreign Policy
87
51
High School Macroeconomics
92
52
Computer Security
84
53
Moral Scenarios
70
54
Moral Disputes
74
55
Electrical Engineering
80
56
Astronomy
93
57
College Biology
95

LLAMA 3.3 70B

Model 8 of 9
Swipe left/right to change models
Average
84%
#
Task
Score
1
High School European History
85
2
Business Ethics
81
3
Clinical Knowledge
87
4
Medical Genetics
95
5
High School Us History
94
6
High School Physics
78
7
High School World History
93
8
Virology
57
9
High School Microeconomics
95
10
Econometrics
70
11
College Computer Science
79
12
High School Biology
94
13
Abstract Algebra
72
14
Professional Accounting
82
15
Philosophy
83
16
Professional Medicine
94
17
Nutrition
89
18
Global Facts
68
19
Machine Learning
76
20
Security Studies
83
21
Public Relations
76
22
Professional Psychology
85
23
Prehistory
88
24
Anatomy
83
25
Human Sexuality
89
26
College Medicine
82
27
High School Government And Politics
98
28
College Chemistry
66
29
Logical Fallacies
85
30
High School Geography
94
31
Elementary Mathematics
89
32
Human Aging
83
33
College Mathematics
76
34
High School Psychology
96
35
Formal Logic
66
36
High School Statistics
84
37
International Law
88
38
High School Mathematics
76
39
High School Computer Science
94
40
Conceptual Physics
85
41
Miscellaneous
95
42
High School Chemistry
81
43
Marketing
94
44
Professional Law
65
45
Management
89
46
College Physics
84
47
Jurisprudence
87
48
World Religions
89
49
Sociology
92
50
Us Foreign Policy
92
51
High School Macroeconomics
89
52
Computer Security
87
53
Moral Scenarios
78
54
Moral Disputes
85
55
Electrical Engineering
81
56
Astronomy
92
57
College Biology
94

GPT 4o Mini

Model 9 of 9
Swipe left/right to change models
Average
82%
#
Task
Score
1
High School European History
85
2
Business Ethics
75
3
Clinical Knowledge
87
4
Medical Genetics
92
5
High School Us History
90
6
High School Physics
77
7
High School World History
89
8
Virology
54
9
High School Microeconomics
93
10
Econometrics
66
11
College Computer Science
75
12
High School Biology
91
13
Abstract Algebra
67
14
Professional Accounting
78
15
Philosophy
79
16
Professional Medicine
90
17
Nutrition
84
18
Global Facts
51
19
Machine Learning
67
20
Security Studies
76
21
Public Relations
75
22
Professional Psychology
83
23
Prehistory
84
24
Anatomy
81
25
Human Sexuality
88
26
College Medicine
81
27
High School Government And Politics
95
28
College Chemistry
60
29
Logical Fallacies
86
30
High School Geography
94
31
Elementary Mathematics
94
32
Human Aging
81
33
College Mathematics
71
34
High School Psychology
93
35
Formal Logic
61
36
High School Statistics
80
37
International Law
90
38
High School Mathematics
84
39
High School Computer Science
91
40
Conceptual Physics
82
41
Miscellaneous
91
42
High School Chemistry
79
43
Marketing
94
44
Professional Law
54
45
Management
87
46
College Physics
84
47
Jurisprudence
84
48
World Religions
87
49
Sociology
91
50
Us Foreign Policy
90
51
High School Macroeconomics
89
52
Computer Security
85
53
Moral Scenarios
61
54
Moral Disputes
82
55
Electrical Engineering
79
56
Astronomy
93
57
College Biology
94

USF-1 Mini

Best performance in 28 tasks

High School Mathematics
99
%
Medical Genetics
98
%
College Computer Science
98
%
Elementary Mathematics
98
%
Formal Logic
98
%
College Mathematics
97
%
Astronomy
97
%
College Biology
97
%
High School Psychology
96
%
High School Biology
95
%
Abstract Algebra
95
%
Miscellaneous
95
%
College Physics
95
%
Professional Medicine
94
%
High School Statistics
94
%
High School Chemistry
93
%
High School Macroeconomics
93
%
World Religions
92
%
Computer Security
92
%
High School Physics
91
%
Logical Fallacies
91
%
Machine Learning
90
%
Electrical Engineering
90
%
Business Ethics
88
%
College Medicine
86
%
Econometrics
85
%
College Chemistry
74
%
Professional Law
73
%
High School Mathematics
99%
Medical Genetics
98%
College Computer Science
99%
High School Mathematics
99%
High School Mathematics
99%
High School Mathematics
99%
High School Mathematics
99%
High School Mathematics
99%
High School Mathematics
99%
High School Mathematics
99%
High School Mathematics
99%
High School Mathematics
99%
High School Mathematics
99%
High School Mathematics
99%
High School Mathematics
99%
High School Mathematics
99%
High School Mathematics
99%
High School Mathematics
99%
High School Mathematics
99%
High School Mathematics
99%
High School Mathematics
99%
High School Mathematics
99%
High School Mathematics
99%
High School Mathematics
99%
High School Mathematics
99%
High School Mathematics
99%
High School Mathematics
99%
High School Mathematics
99%

USF Alpha

Best performance in 8 tasks

High School Government And Politics
99
%
High School Microeconomics
98
%
High School Biology
95
%
Miscellaneous
95
%
Marketing
95
%
Human Aging
87
%
Security Studies
85
%
Virology
60
%

* Data source: MMLU Benchmarks for AI model performance comparison

Color coding: Darker blue = higher scores (better performance), lighter blue = lower scores. This heatmap ranges from dark blue (≥95%) to light blue (below 60%).

Featured Research

Architecture

UltraSafe MERM Architecture: Revolutionizing Expert AI Model Routing

Explore the Multiple Expert Router Model (MERM): smart AI routing that boosts performance across healthcare, finance, and code generation.

Architecture

UltraSafe Cognitive Agent Orchestration Framework: Advanced Multi-Agent Architecture for Enterprise Automation

Discover UltraSafe’s agentic framework: intelligent orchestration enabling autonomous enterprise automation across workflows, decisions, and integrations.

AI Safety

UltraSafe AI Safety Framework: Comprehensive Risk Mitigation in Enterprise AI Systems

Explore AI safety frameworks, risk taxonomies, and mitigation strategies for enterprises—covering robustness, alignment, ethics, and compliance.

View More