Skip to main content

Artificial Analysis Agentic Index (AA Agentic Index)

A display-only Artificial Analysis agentic index.

Benchmark score on AA Agentic Index — May 21, 2026

BenchLM mirrors the published score view for AA Agentic Index. GPT-5.5 leads the public snapshot at 74.1% , followed by Claude Opus 4.7 (Adaptive) (71.3%) and Gemini 3.5 Flash (70.3%). BenchLM does not use these results to rank models overall.

116 modelsAgenticCurrentDisplay onlyUpdated May 21, 2026

The published AA Agentic Index snapshot is tightly clustered at the top: GPT-5.5 sits at 74.1%, while the third row is only 3.8 points behind. The broader top-10 spread is 7.6 points, so many of the published scores sit in a relatively narrow band.

116 models have been evaluated on AA Agentic Index. The benchmark falls in the Agentic category. This category carries a 22% weight in BenchLM.ai's overall scoring system. AA Agentic Index is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About AA Agentic Index

Year

2026

Tasks

Cross-benchmark agentic index

Format

Aggregated model score

Difficulty

Display-only external reference

BenchLM mirrors this agentic index for comparison, but does not use it as a weighted agentic benchmark row.

BenchLM freshness & provenance

Version

AA Agentic 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
74.1%
2
71.3%
3
70.3%
4
68.0%
5
67.6%
6
67.4%
7
67.2%
8
67.0%
9
66.7%
10
66.6%
11
66.1%
12
66.0%
13
65.9%
14
64.8%
15
64.6%
16
64.2%
17
63.1%
18
63.1%
19
62.9%
20
62.8%
21
62.3%
22
62.0%
23
61.7%
24
61.6%
25
61.5%
26
61.3%
27
61.1%
28
60.5%
29
60.2%
30
59.6%
31
59.2%
32
59.1%
33
58.9%
34
58.9%
35
58.9%
36
58.6%
37
58.3%
38
56.5%
39
55.8%
40
55.7%
41
55.0%
42
54.6%
43
54.6%
44
53.3%
45
53.2%
46
53.0%
47
52.0%
48
51.3%
49
50.7%
50
50.7%
52
47.6%
53
47.3%
54
45.8%
55
44.1%
56
43.0%
57
42.9%
58
42.6%
59
42.6%
60
41.5%
61
40.9%
62
40.9%
63
39.8%
64
39.5%
65
39.2%
66
38.3%
67
38.1%
68
38.1%
69
37.9%
70
36.1%
71
35.6%
72
35.0%
73
33.0%
74
32.7%
75
32.1%
76
31.9%
77
31.1%
78
31.1%
79
27.6%
80
27.3%
81
25.9%
82
25.9%
83
25.7%
84
25.1%
85
24.7%
86
24.3%
88
21.7%
89
21.0%
90
20.8%
91
18.9%
92
15.0%
93
13.7%
94
12.7%
95
11.5%
96
10.2%
97
8.8%
98
8.5%
99
8.4%
100
7.6%
101
7.2%
102
7.0%
103
6.9%
104
6.9%
105
6.8%
106
6.5%
107
6.3%
108
5.8%
109
5.2%
110
4.9%
111
4.7%
112
4.4%
113
3.8%
114
3.5%
115
1.4%
116
0.0%

FAQ

What does AA Agentic Index measure?

A display-only Artificial Analysis agentic index.

Which model scores highest on AA Agentic Index?

GPT-5.5 by OpenAI currently leads with a score of 74.1% on AA Agentic Index.

How many models are evaluated on AA Agentic Index?

116 AI models have been evaluated on AA Agentic Index on BenchLM.

Last updated: May 21, 2026 · BenchLM version AA Agentic 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.