Skip to content
Open navigation
OpenOpen workspace

Stack Overflow Developer Survey 2026

AI coding agents: Used in the past year by age

In the Under 18 years old group, 6% selected “BLACKBOX AI”; in the 55-64 years old group, 0% did. Of the 23 answers tested, “BLACKBOX AI” differs most by age, a small association: χ²(7, N = 11739) = 187.73, Holm-adjusted p < .001, V = .13. Respondents could select more than one answer, so the percentages add to more than 100%. These are unweighted respondents, not population estimates.

Published by crosstabs.com · Last updated ·
How results are checkedNamed statistical review pending. Selected automated reference cases are published on the validation page.

The table

The table

Question asked: Have you used any of the following coding agents or assistants in the past year? Do you want to use any of the following in the next 6 months? Respondents could select more than one answer. Shown by age, as the percentage of each group's respondents who selected each answer, with the number of respondents beneath. A respondent is counted in every row they selected, so a column adds to more than 100%.

AI coding agents: Used in the past year by age: percentage of each group's respondents who selected each answer, and respondent counts
AI coding agents: Used in the past yearUnder 18 years old (A)18-24 years old (B)25-34 years old (C)35-44 years old (D)45-54 years old (E)55-64 years old (F)65 years or older (G)Prefer not to say (H)All
Claude Code37.7%8959.7%A78470.1%AB2,35871.3%AB2,61569.9%AB1,35868.8%AB59067.2%A19762.9%A3968.4%8,030
GitHub Copilot66.1%15662.2%81759.2%1,99160.5%2,22165.9%CDG1,28062.9%53953.6%15756.5%3561.3%7,196
OpenAI Codex28.8%6833.5%FG44030.6%F1,02832.0%FG1,17531.5%Fg61224.6%21122.5%6632.3%2030.8%3,620
Cursor19.5%4626.6%FG34928.4%EFGa95429.3%AEFG1,07723.8%g46320.3%17416.0%4727.4%1726.6%3,127
Google Antigravity20.3%G4826.7%CDEFG35116.4%G55115.2%g55715.3%g29713.4%1158.5%2519.4%1216.7%1,956
Gemini Code Assist19.5%C4619.8%CD26012.3%41413.5%49616.3%C31719.7%CD16924.6%CDE7224.2%1515.2%1,789
Open Code17.4%FG4118.9%DEFG24915.7%FG52814.3%FG52412.9%FG2505.8%504.8%149.7%614.2%1,662
JetBrains AI11.0%2611.1%14613.9%46614.0%51213.1%25413.5%11613.7%4014.5%913.4%1,569
Windsurf8.1%198.9%Edg1177.6%e2546.3%2335.4%1046.1%523.8%119.7%66.8%796
Warp6.8%f166.1%F805.7%F1935.7%F2085.4%F1042.7%234.4%136.5%45.5%641
Cline3.4%84.7%625.6%G1874.4%1624.8%g943.6%311.0%36.5%44.7%551
Pi4.7%114.9%F645.2%F1755.0%F1833.7%721.9%162.4%711.3%FGe74.6%535
Amazon Q Developer2.5%63.0%394.1%1384.3%1574.2%824.7%402.7%89.7%64.1%476
Continue3.8%94.3%564.0%1344.3%1584.0%782.5%212.0%66.5%44.0%466
Mistral Vibe5.9%143.8%503.2%1073.5%1293.0%583.0%261.4%48.1%g53.3%393
Kilo Code3.8%95.2%DEG683.5%1192.8%1022.9%563.5%301.0%38.1%G53.3%392
Devin3.4%83.3%443.2%1063.4%1232.3%452.6%222.7%86.5%43.1%360
Google Jules3.8%93.8%f502.5%832.8%1012.1%411.5%131.7%58.1%Fe52.6%307
Replit Agent5.5%CDEf134.8%CDEF632.0%682.0%742.1%401.9%161.7%59.7%CDEFG62.4%285
Tabnine3.8%93.4%D452.3%791.8%652.0%391.6%140.7%26.5%G42.2%257
Aider2.1%51.8%242.1%702.5%932.4%471.3%110.7%26.5%Gf42.2%256
Codium (Qodo)1.7%42.7%E362.0%671.5%561.2%231.2%102.0%66.5%EFd41.8%206
BLACKBOX AI5.9%CDEFG145.7%CDEFG751.7%ef561.0%350.7%130.4%31.0%34.8%EFd31.7%202
Supermaven2.5%f62.4%DEF311.9%DEf631.0%350.8%150.5%40.3%14.8%EFdg31.3%158
Trae3.4%DEF83.0%CDEF391.5%520.8%300.9%170.5%40.3%14.8%DFeg31.3%154
Respondents2361,3143,3643,6701,9438572936211,739

A letter beside a percentage names the columns it is significantly higher than (uppercase 95%, lowercase 90%; pairwise column tests, Bonferroni-corrected). 19,164 of 30,903 respondents have no answer to one of the two questions (not asked or not answered) and are left out. The table shows 25 of the 33 answers: the most selected. The CSV and JSON downloads have every answer.

Analysis

Results

Chi-square test of “BLACKBOX AI”

χ² = 187.73

df = 7, Holm-adjusted p < .001

Effect size

Cramér's V = 0.126

a small association

The strongest answer, APA-style: χ²(7, N = 11739) = 187.73, Holm-adjusted p < .001, V = .13. Each answer is tested on its own, as the respondents who selected it against those who did not, across the 8 groups (N = 11,739). The p-values are Holm-adjusted for the 23 answers tested; 15 of them differ by age at the 0.05 level. 10 answers are not tested: too few respondents selected them for the test to be reliable (an expected count below 1, or more than 20% of the expected counts below 5).

AI coding agents: Used in the past year by age: the test of each answer, selected against not selected, by age
AnswerSelectedχ² (df = 7)Adjusted pCramér's V
Claude Code68.4%170.65< .0010.121
GitHub Copilot61.3%36.05< .0010.055
OpenAI Codex30.8%32.76< .0010.053
Cursor26.6%67.34< .0010.076
Google Antigravity16.7%127.31< .0010.104
Gemini Code Assist15.2%93.86< .0010.089
Open Code14.2%107.18< .0010.096
JetBrains AI13.4%8.92.5160.028
Windsurf6.8%26.24.0050.047
Warp5.5%16.16.1660.037
Cline4.7%18.73.0730.040
Pi4.6%32.20< .0010.052
Amazon Q Developer4.1%13.19.2710.034
Continue4.0%10.43.4960.030
Mistral Vibe3.3%15.20.2000.036
Kilo Code3.3%28.34.0020.049
Devin3.1%8.42.5160.027
Google Jules2.6%23.38.0150.045
Replit Agent2.4%62.15< .0010.073
Tabnine2.2%25.57.0070.047
Aider2.2%15.22.2000.036
Codium (Qodo)1.8%23.08.0150.044
BLACKBOX AI1.7%187.73< .0010.126
Supermaven1.3%Not tested: expected counts too small
Trae1.3%Not tested: expected counts too small

How to read it

No single chi-square test covers this table. A respondent appears in every row they selected, so the rows are not separate groups of people, and a test of the whole table would count the same person several times. Each answer is tested on its own instead: did the share who selected it differ between the groups? Testing 23 answers gives 23 chances of a false alarm, so the p-values are Holm-adjusted to keep the chance of any false alarm in this table at 0.05.

For “BLACKBOX AI” the test rejects independence at the 0.05 level (Holm-adjusted p < .001): differences this large between the groups are unlikely if selecting it did not depend on age. Cramér's V of 0.126 is in the small range, which is real but modest: knowing someone's group tells you only a little about their answer.

With 11,739 respondents, even small differences reach statistical significance. Read the percentages and the effect size before the p-value.

Limits

  • The survey has no weights. These tables are unweighted counts of the people who answered, so they describe the respondents, not developers in general.
  • The test treats respondents as a simple random sample. They are people who chose to answer a survey Stack Overflow promoted, not a random sample of developers, so a result holds for these respondents and may not hold beyond them.
  • The adjustment covers the answers of this question by this group only, not the other tables in the library. The headline answer is the strongest of those tested, so its effect size is larger than a typical answer's.
  • A difference between groups is not evidence that group membership causes the answer.

Next steps

Work with this table

Open the test of “BLACKBOX AI” in the calculator

The link fills in the respondents who selected this answer and those who did not, by group. The whole table does not open there: its rows overlap, and the calculator's test needs rows that are separate people.

Open this question in the full file

The workspace opens all 30,903 respondents in your browser with this question selected. The survey has no weights, so the table there is unweighted too. Change the group, add a filter or export from there.

Open in the workspace →

Run this on your own data — free, no signup

Upload a CSV, Excel, SPSS, Stata, SAS, R, Parquet or JSON file. Everything runs in your browser; your file never leaves your device.

Open the workspace →

The same question by other groups

Other questions that differ by age

Source

Stack Overflow. 2026 Developer Survey, https://survey.stackoverflow.co/2026, licensed under the ODbL 1.0. Tabulated by crosstabs.com. Variables AICodeAgentHaveWorkedWith (AI coding agents: Used in the past year) and Age. Stack Overflow licenses the survey data under the Open Database License (ODbL) 1.0 and its contents under the Database Contents License (DbCL) 1.0: credit Stack Overflow, keep the licence notice, and share any database made from the data under the ODbL. These tables and their downloads are offered on those terms.

  1. [1]Stack Overflow: 2026 Developer Survey public results (survey_results_public.csv)survey.stackoverflow.co
  2. [2]Stack Overflow: Open Database License (ODbL) 1.0opendatacommons.org