Skip to content
Open navigation
OpenOpen workspace

Stack Overflow Developer Survey 2026

AI coding agents: Want to use in the next 6 months by age

In the 65 years or older group, 23% selected “Gemini Code Assist”; in the 25-34 years old group, 8% did. Of the 33 answers tested, “Gemini Code Assist” differs most by age, a small association: χ²(7, N = 7648) = 88.18, Holm-adjusted p < .001, V = .11. 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: Want to use in the next 6 months by age: percentage of each group's respondents who selected each answer, and respondent counts
AI coding agents: Want to use in the next 6 monthsUnder 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 Code55.1%7564.2%56265.9%1,50168.3%A1,63265.6%78167.8%37765.2%12067.6%2566.3%5,073
GitHub Copilot36.8%5029.8%26129.6%67429.9%71436.7%BCD43735.3%19633.2%6129.7%1131.4%2,404
OpenAI Codex30.9%4232.6%DFc28527.2%62026.9%64231.1%37024.6%13722.3%4140.5%1528.1%2,152
Cursor20.6%2823.7%CFGe20718.3%41719.1%45618.3%21814.2%7912.5%2321.6%818.8%1,436
Open Code24.3%FG3322.7%FGd19920.9%FG47518.1%F43318.2%F21710.1%569.8%1813.5%518.8%1,436
Google Antigravity22.1%C3021.0%CDF18412.0%27413.7%32816.0%C19112.4%6914.1%2624.3%914.5%1,111
Gemini Code Assist11.0%1512.2%C1077.8%17810.2%24314.4%CD17117.1%CD9522.8%BCDe4218.9%711.2%858
Pi11.8%1613.1%Fg11511.4%F26010.5%25210.1%1206.5%365.4%1013.5%510.6%814
JetBrains AI8.1%1111.8%10310.0%2289.2%21911.7%13911.9%6612.5%235.4%210.3%791
Mistral Vibe8.1%119.7%857.0%1606.9%1647.7%926.3%356.0%118.1%37.3%561
Windsurf7.4%109.8%CDEF864.8%1094.6%1095.4%644.1%234.9%95.4%25.4%412
Warp5.1%79.1%CDEF804.6%1044.3%1034.4%522.5%144.3%85.4%24.8%370
Devin7.4%108.3%CDEF734.5%1034.4%1063.9%473.4%194.3%82.7%14.8%367
Amazon Q Developer5.9%87.4%CD654.1%934.3%1035.2%624.5%253.3%65.4%24.8%364
Kilo Code4.4%67.4%CDEF654.5%1033.9%944.1%493.4%193.8%72.7%14.5%344
Google Jules5.9%88.7%CDEF764.0%923.5%843.9%473.1%176.5%125.4%24.4%338
Cline3.7%57.8%CDEf683.9%893.9%934.0%483.8%213.8%75.4%24.4%333
Continue5.1%77.0%CDef613.6%833.4%814.0%483.2%183.3%62.7%14.0%305
Replit Agent3.7%57.2%CDEF633.2%742.7%653.6%432.9%164.3%82.7%13.6%275
Aider2.2%36.4%CDFe563.6%822.8%673.5%422.5%143.8%75.4%23.6%273
Emdash4.4%66.6%CDFe582.8%632.7%653.8%452.2%122.2%48.1%33.3%256
BLACKBOX AI3.7%56.6%CDEF583.2%722.5%602.9%352.0%113.8%78.1%33.3%251
Codium (Qodo)2.9%46.7%CDEF593.0%682.5%603.3%392.3%132.7%52.7%13.3%249
Supermaven4.4%67.0%CDEF612.9%662.3%542.9%342.2%123.3%62.7%13.1%240
Augment Code3.7%56.2%CDEF542.7%612.5%593.1%372.0%112.7%52.7%13.0%233
Respondents1368752,2782,3911,191556184377,648

A letter beside a percentage names the columns it is significantly higher than (uppercase 95%, lowercase 90%; pairwise column tests, Bonferroni-corrected). 23,255 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 “Gemini Code Assist”

χ² = 88.18

df = 7, Holm-adjusted p < .001

Effect size

Cramér's V = 0.107

a small association

The strongest answer, APA-style: χ²(7, N = 7648) = 88.18, Holm-adjusted p < .001, V = .11. Each answer is tested on its own, as the respondents who selected it against those who did not, across the 8 groups (N = 7,648). The p-values are Holm-adjusted for the 33 answers tested; 30 of them differ by age at the 0.05 level.

AI coding agents: Want to use in the next 6 months by age: the test of each answer, selected against not selected, by age
AnswerSelectedχ² (df = 7)Adjusted pCramér's V
Claude Code66.3%14.49.1300.044
GitHub Copilot31.4%28.52.0020.061
OpenAI Codex28.1%26.28.0040.059
Cursor18.8%27.16.0030.060
Open Code18.8%57.14< .0010.086
Google Antigravity14.5%55.80< .0010.085
Gemini Code Assist11.2%88.18< .0010.107
Pi10.6%23.51.0080.055
JetBrains AI10.3%12.12.1940.040
Mistral Vibe7.3%10.20.1940.037
Windsurf5.4%41.53< .0010.074
Warp4.8%44.28< .0010.076
Devin4.8%31.74< .0010.064
Amazon Q Developer4.8%19.06.0320.050
Kilo Code4.5%21.69.0140.053
Google Jules4.4%48.91< .0010.080
Cline4.4%28.00.0020.061
Continue4.0%25.01.0050.057
Replit Agent3.6%40.11< .0010.072
Aider3.6%27.38.0030.060
Emdash3.3%41.39< .0010.074
BLACKBOX AI3.3%41.83< .0010.074
Codium (Qodo)3.3%40.27< .0010.073
Supermaven3.1%51.65< .0010.082
Augment Code3.0%35.12< .0010.068

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 33 answers gives 33 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 “Gemini Code Assist” 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 0.107 is in the small range, which is real but modest: knowing someone's group tells you only a little about their answer.

With 7,648 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 “Gemini Code Assist” 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 AICodeAgentWantToUseNext6Months (AI coding agents: Want to use in the next 6 months) 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