Skip to main content

Artificial Analysis Coding Index (AA Coding Index)

A display-only Artificial Analysis coding index.

Benchmark score on AA Coding Index — May 21, 2026

BenchLM mirrors the published score view for AA Coding Index. GPT-5.5 leads the public snapshot at 59.1% , followed by GPT-5.4 (57.3%) and Gemini 3.1 Pro (55.5%). BenchLM does not use these results to rank models overall.

122 modelsCodingCurrentDisplay onlyUpdated May 21, 2026

The published AA Coding Index snapshot is tightly clustered at the top: GPT-5.5 sits at 59.1%, while the third row is only 3.6 points behind. The broader top-10 spread is 11.0 points, so the benchmark still separates strong models even when the leaders cluster.

122 models have been evaluated on AA Coding Index. The benchmark falls in the Coding category. This category carries a 20% weight in BenchLM.ai's overall scoring system. AA Coding Index is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About AA Coding Index

Year

2026

Tasks

Cross-benchmark coding index

Format

Aggregated model score

Difficulty

Display-only external reference

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

BenchLM freshness & provenance

Version

AA Coding 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 (122 models)

1
59.1%
2
57.3%
3
55.5%
4
53.1%
5
53.1%
6
52.5%
7
51.5%
8
50.1%
9
48.7%
10
48.1%
11
47.8%
12
47.6%
13
47.5%
14
47.5%
15
47.1%
16
46.5%
17
46.4%
18
45.5%
19
45.0%
20
44.9%
21
44.7%
22
44.2%
23
44.2%
24
43.9%
25
43.4%
26
43.3%
27
43.0%
28
42.9%
29
42.9%
30
41.9%
31
41.4%
32
41.3%
33
41.0%
34
40.5%
35
39.8%
36
39.5%
37
39.5%
38
39.0%
39
38.7%
40
38.7%
41
38.4%
42
37.8%
43
37.4%
44
36.8%
45
36.6%
46
36.6%
47
36.5%
48
36.5%
49
36.5%
50
36.3%
51
36.2%
52
36.0%
53
35.5%
54
35.4%
55
35.1%
56
34.9%
57
34.7%
58
34.6%
59
34.0%
60
31.9%
62
30.6%
63
30.3%
64
30.2%
65
30.1%
66
29.7%
67
29.3%
68
28.6%
69
28.4%
70
27.4%
71
27.2%
72
27.2%
73
27.0%
74
26.4%
75
25.8%
76
25.2%
77
24.3%
78
24.3%
79
24.0%
80
23.8%
81
23.7%
82
23.6%
83
23.2%
84
22.7%
85
22.4%
86
22.1%
87
22.0%
88
21.8%
89
21.5%
90
20.5%
91
19.5%
92
19.5%
93
18.5%
94
18.5%
95
17.9%
96
17.8%
97
16.7%
98
16.4%
99
15.8%
100
15.6%
102
14.5%
103
13.8%
104
13.7%
105
13.6%
106
13.1%
107
11.3%
108
11.2%
109
11.2%
110
11.0%
111
9.8%
112
9.6%
113
9.4%
114
9.0%
115
7.9%
116
6.7%
117
6.7%
118
2.9%
119
2.7%
120
2.5%
121
0.6%
122
0.3%

FAQ

What does AA Coding Index measure?

A display-only Artificial Analysis coding index.

Which model scores highest on AA Coding Index?

GPT-5.5 by OpenAI currently leads with a score of 59.1% on AA Coding Index.

How many models are evaluated on AA Coding Index?

122 AI models have been evaluated on AA Coding Index on BenchLM.

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