Skip to main content

Artificial Analysis Omniscience Accuracy (AA-Omniscience Accuracy)

A display-only Artificial Analysis knowledge metric for the proportion of correctly answered questions.

Benchmark score on AA-Omniscience Accuracy — June 2, 2026

BenchLM mirrors the published score view for AA-Omniscience Accuracy. GPT-5.5 leads the public snapshot at 56.9% , followed by Gemini 3 Pro (55.9%) and Gemini 3.1 Pro (55.3%). BenchLM does not use these results to rank models overall.

115 modelsKnowledgeCurrentDisplay onlyUpdated June 2, 2026

The published AA-Omniscience Accuracy snapshot is tightly clustered at the top: GPT-5.5 sits at 56.9%, while the third row is only 1.6 points behind. The broader top-10 spread is 11.2 points, so the benchmark still separates strong models even when the leaders cluster.

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

About AA-Omniscience Accuracy

Year

2026

Tasks

Knowledge questions

Format

Accuracy

Difficulty

Broad knowledge

BenchLM stores AA-Omniscience Accuracy as a display-only row when a model page publishes the exact Artificial Analysis benchmark card value.

BenchLM freshness & provenance

Version

AA-Omniscience Accuracy 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 (115 models)

1
56.9%
2
55.9%
3
55.3%
4
51.9%
5
51.8%
6
50.0%
7
46.6%
8
46.4%
9
45.8%
10
45.7%
11
45.5%
12
45.2%
13
44.6%
14
43.8%
15
43.5%
16
43.3%
17
41.8%
18
41.4%
19
40.7%
20
40.7%
21
40.7%
22
39.2%
23
39.2%
24
39.0%
25
38.9%
26
38.4%
27
38.0%
28
37.7%
29
37.6%
30
37.5%
31
37.2%
32
36.4%
33
35.5%
34
34.7%
35
34.6%
36
34.3%
37
34.3%
38
32.8%
39
31.4%
40
31.0%
41
30.1%
42
29.3%
43
29.1%
44
29.0%
45
28.8%
46
28.0%
47
26.9%
48
26.8%
49
26.8%
50
26.5%
51
26.2%
52
26.1%
53
25.4%
54
25.4%
55
25.4%
57
25.1%
58
24.7%
59
24.4%
60
24.3%
61
24.3%
62
24.2%
63
24.2%
64
24.2%
65
24.1%
66
23.8%
67
23.1%
68
22.8%
69
22.8%
70
22.6%
71
22.6%
72
22.4%
73
22.3%
74
22.1%
75
22.1%
76
21.5%
77
21.0%
78
20.8%
79
20.5%
80
20.1%
81
19.9%
82
19.9%
83
19.7%
84
19.2%
85
18.9%
86
18.7%
87
18.3%
88
18.2%
89
17.6%
90
17.5%
91
17.2%
92
17.0%
93
17.0%
94
16.5%
95
15.6%
96
15.5%
97
15.5%
98
15.4%
99
15.2%
101
14.6%
102
13.3%
103
13.2%
104
12.7%
105
12.5%
106
11.4%
107
10.4%
108
8.9%
109
8.6%
110
6.7%
111
6.1%
112
5.3%
113
4.7%
114
3.7%
115
3.2%

FAQ

What does AA-Omniscience Accuracy measure?

A display-only Artificial Analysis knowledge metric for the proportion of correctly answered questions.

Which model scores highest on AA-Omniscience Accuracy?

GPT-5.5 by OpenAI currently leads with a score of 56.9% on AA-Omniscience Accuracy.

How many models are evaluated on AA-Omniscience Accuracy?

115 AI models have been evaluated on AA-Omniscience Accuracy on BenchLM.

Last updated: June 2, 2026 · BenchLM version AA-Omniscience Accuracy 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.