Skip to content
Open navigation
OpenOpen workspace

Stack Overflow Developer Survey 2026

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

In the Prefer to self-describe: group, 14% selected “Emdash”; in the Man group, 3% did. Of the 33 answers tested, “Emdash” differs most by gender, a small association: χ²(4, N = 7617) = 78.43, Holm-adjusted p < .001, V = .10. 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 gender, 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 gender: percentage of each group's respondents who selected each answer, and respondent counts
AI coding agents: Want to use in the next 6 monthsMan (A)Non-binary (B)Prefer not to say (C)Prefer to self-describe: (D)Woman (E)All
Claude Code66.6%c4,53956.8%5457.5%12352.5%3171.3%CDb30866.4%5,055
GitHub Copilot31.3%2,13430.5%2928.5%6125.4%1536.3%15731.5%2,396
OpenAI Codex28.2%1,91932.6%3127.1%5833.9%2026.4%11428.1%2,142
Open Code18.8%1,28515.8%1522.0%4722.0%1317.1%7418.8%1,434
Cursor18.8%1,28513.7%1315.0%3213.6%821.5%9318.8%1,431
Google Antigravity14.4%98511.6%1115.4%3313.6%816.0%6914.5%1,106
Gemini Code Assist11.2%7616.3%69.8%2118.6%1113.4%5811.3%857
Pi10.3%70018.9%a1813.6%2918.6%1112.7%5510.7%813
JetBrains AI9.9%6748.4%813.6%2913.6%816.0%A6910.3%788
Mistral Vibe7.0%4756.3%67.5%1610.2%613.0%A567.3%559
Windsurf5.0%3405.3%57.5%1610.2%610.4%A455.4%412
Warp4.5%3095.3%56.1%1310.2%68.6%A374.9%370
Devin4.4%3016.3%66.1%1310.2%69.3%A404.8%366
Amazon Q Developer4.3%2964.2%46.1%138.5%510.6%A464.8%364
Kilo Code4.1%2814.2%46.1%1311.9%A79.0%A394.5%344
Google Jules4.0%2754.2%45.1%1110.2%69.5%A414.4%337
Cline4.0%2723.2%36.1%1310.2%69.0%A394.4%333
Continue3.6%2484.2%43.7%810.2%a69.0%A394.0%305
Replit Agent3.2%2202.1%24.7%108.5%58.8%A383.6%275
Aider3.1%2143.2%36.1%1311.9%A78.3%A363.6%273
Emdash2.8%1923.2%35.6%1213.6%A89.5%A413.4%256
BLACKBOX AI2.8%1922.1%25.1%1110.2%A69.3%A403.3%251
Codium (Qodo)2.9%1962.1%23.7%811.9%A78.3%A363.3%249
Supermaven2.8%1882.1%24.2%98.5%a58.3%A363.2%240
Augment Code2.7%1823.2%34.7%108.5%a57.6%A333.1%233
Respondents6,81795214594327,617

A letter beside a percentage names the columns it is significantly higher than (uppercase 95%, lowercase 90%; pairwise column tests, Bonferroni-corrected). 23,286 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 “Emdash”

χ² = 78.43

df = 4, Holm-adjusted p < .001

Effect size

Cramér's V = 0.101

a small association

The strongest answer, APA-style: χ²(4, N = 7617) = 78.43, Holm-adjusted p < .001, V = .10. Each answer is tested on its own, as the respondents who selected it against those who did not, across the 5 groups (N = 7,617). The p-values are Holm-adjusted for the 33 answers tested; 27 of them differ by gender at the 0.05 level.

AI coding agents: Want to use in the next 6 months by gender: the test of each answer, selected against not selected, by gender
AnswerSelectedχ² (df = 4)Adjusted pCramér's V
Claude Code66.4%21.34.0030.053
GitHub Copilot31.5%6.76.7110.030
OpenAI Codex28.1%2.681.0000.019
Open Code18.8%3.161.0000.020
Cursor18.8%6.88.7110.030
Google Antigravity14.5%1.611.0000.015
Gemini Code Assist11.3%8.09.5300.033
Pi10.7%15.70.0240.045
JetBrains AI10.3%19.70.0050.051
Mistral Vibe7.3%22.32.0020.054
Windsurf5.4%27.95< .0010.061
Warp4.9%18.72.0070.050
Devin4.8%25.94< .0010.058
Amazon Q Developer4.8%38.19< .0010.071
Kilo Code4.5%31.46< .0010.064
Google Jules4.4%33.55< .0010.066
Cline4.4%31.34< .0010.064
Continue4.0%36.63< .0010.069
Replit Agent3.6%41.59< .0010.074
Aider3.6%47.70< .0010.079
Emdash3.4%78.43< .0010.101
BLACKBOX AI3.3%64.58< .0010.092
Codium (Qodo)3.3%52.72< .0010.083
Supermaven3.2%48.07< .0010.079
Augment Code3.1%41.76< .0010.074

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 “Emdash” 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 gender. Cramér's V of 0.101 is in the small range, which is real but modest: knowing someone's group tells you only a little about their answer.

With 7,617 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 “Emdash” 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 gender

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 Gender. 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