Skip to content
Open navigation
OpenOpen workspace

Stack Overflow Developer Survey 2026

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

In the Hybrid (some in-person, leans heavy to flexibility) group, 36% selected “GitHub Copilot”; in the Remote group, 27% did. Of the 33 answers tested, “GitHub Copilot” differs most by work setting, a negligible association: χ²(4, N = 6691) = 34.50, Holm-adjusted p < .001, V = .07. 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 work setting, 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 work setting: percentage of each group's respondents who selected each answer, and respondent counts
AI coding agents: Want to use in the next 6 monthsHybrid (some in-person, leans heavy to flexibility) (A)Hybrid (some remote, leans heavy to in-person) (B)In-person (C)Remote (D)Your choice (very flexible, you can come in when you want or just as needed) (E)All
Claude Code66.8%71268.5%92164.3%60068.6%1,65365.7%61567.3%4,501
GitHub Copilot35.7%D38132.5%D43732.2%D30026.8%64532.5%D30430.9%2,067
OpenAI Codex23.9%25526.6%35830.8%AE28729.3%AE70724.0%22527.4%1,832
Open Code16.6%17718.6%25016.9%15818.0%43319.9%18618.0%1,204
Cursor15.5%16516.7%22419.8%18519.0%45917.7%16617.9%1,199
Google Antigravity13.5%14413.2%17815.4%14412.3%29712.4%11613.1%879
Gemini Code Assist10.6%1139.3%12513.9%BD1308.4%20311.1%10410.1%675
Pi9.6%1029.3%1258.6%8010.7%25911.5%10810.1%674
JetBrains AI10.6%11310.3%13910.2%958.2%19811.4%D1079.7%652
Mistral Vibe6.9%747.7%D1037.2%675.3%1288.4%D796.7%451
Windsurf4.7%504.2%566.0%d563.9%935.3%504.6%305
Warp3.6%383.9%535.0%473.9%944.6%434.1%275
Amazon Q Developer3.6%383.6%485.9%Db553.4%825.0%474.0%270
Devin4.0%433.6%485.5%513.6%864.4%414.0%269
Kilo Code3.7%393.0%406.1%BD573.3%794.8%453.9%260
Cline2.5%273.6%495.4%Ad503.3%804.6%433.7%249
Google Jules3.7%392.5%345.7%BD532.8%683.8%363.4%230
Continue2.8%302.9%395.7%ABD532.4%583.8%363.2%216
Aider2.4%262.6%354.6%Dab432.4%573.6%342.9%195
Replit Agent2.3%242.5%335.1%ABD482.2%533.5%332.9%191
Emdash2.3%242.5%333.8%D351.9%474.1%D382.6%177
Codium (Qodo)2.2%232.4%324.6%ABD431.9%463.3%312.6%175
BLACKBOX AI2.3%242.2%304.3%Dab401.7%423.7%D352.6%171
Supermaven2.9%311.9%253.9%BD361.7%423.4%D322.5%166
Augment Code2.3%251.8%244.2%BD391.6%393.5%Db332.4%160
Respondents1,0661,3459332,4119366,691

A letter beside a percentage names the columns it is significantly higher than (uppercase 95%, lowercase 90%; pairwise column tests, Bonferroni-corrected). 24,212 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 “GitHub Copilot”

χ² = 34.50

df = 4, Holm-adjusted p < .001

Effect size

Cramér's V = 0.072

a negligible association

The strongest answer, APA-style: χ²(4, N = 6691) = 34.50, Holm-adjusted p < .001, V = .07. Each answer is tested on its own, as the respondents who selected it against those who did not, across the 5 groups (N = 6,691). The p-values are Holm-adjusted for the 33 answers tested; 19 of them differ by work setting at the 0.05 level.

AI coding agents: Want to use in the next 6 months by work setting: the test of each answer, selected against not selected, by work setting
AnswerSelectedχ² (df = 4)Adjusted pCramér's V
Claude Code67.3%7.58.6490.034
GitHub Copilot30.9%34.50< .0010.072
OpenAI Codex27.4%22.01.0050.057
Open Code18.0%4.66.6490.026
Cursor17.9%10.17.3020.039
Google Antigravity13.1%6.32.6490.031
Gemini Code Assist10.1%24.93.0010.061
Pi10.1%6.93.6490.032
JetBrains AI9.7%11.09.2300.041
Mistral Vibe6.7%14.32.0700.046
Windsurf4.6%9.04.4210.037
Warp4.1%3.77.6490.024
Amazon Q Developer4.0%14.55.0690.047
Devin4.0%7.36.6490.033
Kilo Code3.9%20.02.0090.055
Cline3.7%14.29.0700.046
Google Jules3.4%20.89.0070.056
Continue3.2%25.38.0010.062
Aider2.9%15.07.0600.047
Replit Agent2.9%25.09.0010.061
Emdash2.6%17.07.0280.051
Codium (Qodo)2.6%22.25.0040.058
BLACKBOX AI2.6%23.88.0020.060
Supermaven2.5%19.12.0130.053
Augment Code2.4%26.27< .0010.063

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 “GitHub Copilot” 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 work setting. Cramér's V of 0.072 is in the negligible range, which is trivially weak in practical terms, even where a sample this large can detect it.

With 6,691 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 “GitHub Copilot” 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 work setting

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 WorkSetting. 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