Skip to main content

Artificial Analysis Omniscience Index (AA-Omniscience Index)

A display-only Artificial Analysis factual knowledge index.

Benchmark score on AA-Omniscience Index — May 21, 2026

BenchLM mirrors the published score view for AA-Omniscience Index. Gemini 3.1 Pro leads the public snapshot at 32.9% , followed by Claude Opus 4.7 (Adaptive) (26.2%) and Gemini 3.5 Flash (22.7%). BenchLM does not use these results to rank models overall.

116 modelsKnowledgeCurrentDisplay onlyUpdated May 21, 2026

The published AA-Omniscience Index snapshot is tightly clustered at the top: Gemini 3.1 Pro sits at 32.9%, while the third row is only 10.2 points behind. The broader top-10 spread is 19.6 points, so the benchmark still separates strong models even when the leaders cluster.

116 models have been evaluated on AA-Omniscience Index. The benchmark falls in the Knowledge category. This category carries a 12% weight in BenchLM.ai's overall scoring system. AA-Omniscience Index is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About AA-Omniscience Index

Year

2026

Tasks

Knowledge questions

Format

Index score

Difficulty

Broad factual knowledge

BenchLM stores the AA-Omniscience index as a display-only factuality signal alongside the accuracy and hallucination-rate rows.

BenchLM freshness & provenance

Version

AA-Omniscience Index 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

Benchmark score table (116 models)

1
32.9%
2
26.2%
3
22.7%
4
20.1%
5
18.3%
6
15.8%
7
14.2%
8
14.1%
9
13.5%
10
13.3%
11
10.2%
12
9.9%
13
6.4%
14
5.7%
15
5.6%
16
4.9%
17
4.1%
18
3.8%
19
3.6%
20
3.5%
21
2.7%
22
2.0%
23
2.0%
24
1.9%
25
0.7%
26
-1.0%
27
-2.5%
28
-2.9%
29
-3.6%
30
-3.9%
31
-4.0%
32
-6.0%
33
-6.0%
34
-6.0%
35
-8.1%
36
-8.1%
37
-8.1%
38
-9.2%
39
-9.7%
40
-10.0%
41
-10.1%
42
-10.5%
43
-10.7%
44
-14.3%
45
-15.1%
46
-15.3%
47
-15.5%
48
-17.3%
49
-17.4%
50
-18.7%
51
-19.0%
52
-19.8%
53
-20.0%
54
-21.4%
55
-22.3%
56
-22.9%
57
-24.0%
58
-27.1%
59
-27.5%
60
-28.4%
61
-28.4%
62
-28.7%
63
-29.5%
64
-29.8%
65
-29.9%
66
-29.9%
67
-31.5%
68
-31.6%
69
-34.0%
70
-34.6%
71
-34.6%
72
-36.0%
73
-36.1%
74
-36.2%
75
-36.3%
76
-39.4%
77
-39.6%
78
-41.1%
79
-41.3%
80
-41.8%
81
-42.0%
82
-42.0%
83
-43.1%
84
-44.2%
85
-44.2%
86
-44.6%
87
-45.4%
88
-45.5%
89
-46.4%
90
-46.7%
91
-47.6%
92
-47.6%
93
-48.1%
94
-48.5%
95
-50.0%
96
-50.1%
97
-50.9%
98
-52.4%
100
-56.4%
101
-56.7%
102
-57.9%
103
-59.5%
104
-61.7%
105
-62.3%
106
-62.5%
107
-63.9%
108
-65.7%
109
-65.9%
110
-69.2%
111
-72.0%
112
-72.1%
113
-73.6%
114
-81.8%
115
-82.6%
116
-87.2%

FAQ

What does AA-Omniscience Index measure?

A display-only Artificial Analysis factual knowledge index.

Which model scores highest on AA-Omniscience Index?

Gemini 3.1 Pro by Google currently leads with a score of 32.9% on AA-Omniscience Index.

How many models are evaluated on AA-Omniscience Index?

116 AI models have been evaluated on AA-Omniscience Index on BenchLM.

Last updated: May 21, 2026 · BenchLM version AA-Omniscience Index 2026

The AI models change fast. We track them for you.

For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.