Skip to main content

Artificial Analysis Intelligence Index

A display-only intelligence index published by Artificial Analysis that aggregates provider-reported and benchmark-derived signals into a single model-level score.

Benchmark score on Artificial Analysis Intelligence Index — June 2, 2026

BenchLM mirrors the published score view for Artificial Analysis Intelligence Index. Claude Opus 4.8 leads the public snapshot at 61.4% , followed by GPT-5.5 (60.2%) and Claude Opus 4.7 (Adaptive) (57.3%). BenchLM does not use these results to rank models overall.

128 modelsKnowledgeCurrentDisplay onlyUpdated June 2, 2026

The published Artificial Analysis Intelligence Index snapshot is tightly clustered at the top: Claude Opus 4.8 sits at 61.4%, while the third row is only 4.2 points behind. The broader top-10 spread is 7.9 points, so many of the published scores sit in a relatively narrow band.

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

About Artificial Analysis Intelligence Index

Year

2026

Tasks

Cross-benchmark intelligence index

Format

Aggregated model score

Difficulty

Display-only external reference

BenchLM tracks Artificial Analysis as a display-only external reference rather than a weighted benchmark. It is useful as a market snapshot, but it is not a benchmark-native row with a single public task set, scoring harness, or exact-source methodology aligned to BenchLM's core benchmark pages.

BenchLM freshness & provenance

Version

Artificial Analysis Intelligence 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 (128 models)

1
61.4%
2
60.2%
3
57.3%
4
57.2%
5
56.8%
6
56.6%
7
55.3%
8
53.9%
9
53.8%
10
53.6%
11
53.2%
12
53.0%
13
52.1%
14
51.8%
15
51.8%
16
51.5%
17
51.4%
18
51.3%
19
50.0%
20
49.8%
21
49.8%
22
49.7%
23
49.6%
24
49.2%
25
49.0%
26
48.9%
27
48.4%
28
47.7%
29
46.8%
30
46.8%
31
46.8%
32
46.5%
33
46.5%
34
46.0%
35
45.8%
36
45.0%
37
44.6%
38
44.4%
39
44.0%
40
43.5%
41
43.4%
42
43.1%
43
43.1%
44
43.1%
45
42.9%
46
42.6%
47
42.1%
48
42.1%
49
42.0%
50
42.0%
51
41.9%
52
41.6%
53
41.5%
54
40.7%
55
40.1%
56
39.2%
57
39.2%
59
38.4%
60
37.2%
61
37.1%
62
36.0%
63
35.1%
64
35.0%
65
34.6%
66
33.5%
67
33.3%
68
33.0%
69
32.1%
70
32.1%
71
31.9%
72
31.9%
73
31.4%
74
31.2%
75
30.8%
76
30.4%
77
30.2%
78
28.7%
79
28.1%
80
27.8%
81
27.8%
82
27.7%
83
27.1%
84
26.3%
85
26.3%
86
26.2%
87
25.9%
88
25.8%
89
24.5%
90
23.7%
91
23.6%
92
23.2%
93
22.9%
94
22.8%
96
20.6%
97
18.8%
98
18.8%
99
18.4%
100
18.2%
101
18.0%
102
17.4%
103
17.3%
104
17.2%
105
16.5%
106
16.0%
107
15.2%
108
15.1%
109
15.0%
110
13.7%
111
13.6%
112
13.5%
113
13.5%
114
13.2%
115
13.0%
116
12.9%
117
12.7%
118
12.3%
119
12.3%
120
11.7%
121
10.4%
122
10.3%
123
8.5%
124
8.1%
125
8.0%
126
7.3%
127
6.1%
128
5.4%

FAQ

What does Artificial Analysis Intelligence Index measure?

A display-only intelligence index published by Artificial Analysis that aggregates provider-reported and benchmark-derived signals into a single model-level score.

Which model scores highest on Artificial Analysis Intelligence Index?

Claude Opus 4.8 by Anthropic currently leads with a score of 61.4% on Artificial Analysis Intelligence Index.

How many models are evaluated on Artificial Analysis Intelligence Index?

128 AI models have been evaluated on Artificial Analysis Intelligence Index on BenchLM.

Last updated: June 2, 2026 · BenchLM version Artificial Analysis Intelligence 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.