Skip to content
Open navigation
OpenOpen workspace

Stack Overflow Developer Survey 2026

AI coding agents: Used in the past year by employment status

In the I prefer not to say group, 10% selected “BLACKBOX AI”; in the Employed group, 1% did. Of the 27 answers tested, “BLACKBOX AI” differs most by employment status, a small association: χ²(5, N = 11739) = 234.17, Holm-adjusted p < .001, V = .14. 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 employment status, 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 employment status: percentage of each group's respondents who selected each answer, and respondent counts
AI coding agents: Used in the past yearEmployed (A)I prefer not to say (B)Independent contractor, freelancer, or self-employed (C)Not employed (D)Retired (E)Student (F)All
Claude Code70.2%BDEF5,87854.9%6273.0%BDEF1,23262.3%F34852.9%9250.1%41868.4%8,030
GitHub Copilot62.2%CE5,21058.4%6656.7%95760.3%E33746.6%8165.3%CE54561.3%7,196
OpenAI Codex29.5%2,47038.1%4337.7%AEF63731.8%17824.7%4329.8%24930.8%3,620
Cursor26.5%EF2,21731.0%E3529.4%EF49632.0%EFa17915.5%2720.7%17326.6%3,127
Google Antigravity14.3%1,19928.3%AE3222.2%AE37422.0%AE1239.8%1725.3%AE21116.7%1,956
Gemini Code Assist12.3%1,02624.8%A2821.2%A35824.3%A13629.9%A5222.6%A18915.2%1,789
Open Code13.3%1,11326.5%ACE3015.2%E25719.0%AE1066.9%1217.2%AE14414.2%1,662
JetBrains AI13.1%1,09415.9%1815.9%AF26912.7%7113.2%2311.3%9413.4%1,569
Windsurf6.1%51017.7%ACDEF209.0%AE1527.7%432.3%48.0%676.8%796
Warp5.0%41815.9%ACDEF187.2%A1225.9%334.6%85.0%425.5%641
Cline4.6%38111.5%AEF135.5%925.5%311.1%23.8%324.7%551
Pi4.0%3349.7%A116.0%A1027.9%Af444.6%84.3%364.6%535
Amazon Q Developer3.9%32311.5%ACEF134.7%795.9%f332.9%52.8%234.1%476
Continue3.4%2858.8%A106.0%A1015.0%285.2%94.0%334.0%466
Mistral Vibe2.8%23312.4%ACDEF144.8%A813.9%222.3%44.7%A393.3%393
Kilo Code2.7%22911.5%ACDEF135.0%A844.5%251.1%24.7%A393.3%392
Devin2.5%20910.6%ACF124.2%A714.8%A274.0%74.1%343.1%360
Google Jules1.6%13816.8%ACDEF194.9%A825.4%A301.7%34.2%A352.6%307
Replit Agent1.5%12311.5%ACDE134.4%A744.5%A252.9%55.4%A452.4%285
Tabnine1.6%1368.8%AEcf103.6%A603.8%A211.1%23.4%A282.2%257
Aider1.9%15510.6%ACDEF123.3%A552.7%151.7%31.9%162.2%256
Codium (Qodo)1.1%9510.6%ACDEF123.4%A573.2%A182.3%42.4%A201.8%206
BLACKBOX AI0.7%609.7%ACE113.2%A544.1%A231.1%26.2%AC521.7%202
Supermaven0.9%729.7%ACDEF112.4%A412.9%A161.1%21.9%A161.3%158
Trae0.7%569.7%ACDEF112.9%A492.9%A160.6%12.5%A211.3%154
Respondents8,3701131,68855917483511,739

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 = 234.17

df = 5, Holm-adjusted p < .001

Effect size

Cramér's V = 0.141

a small association

The strongest answer, APA-style: χ²(5, N = 11739) = 234.17, Holm-adjusted p < .001, V = .14. Each answer is tested on its own, as the respondents who selected it against those who did not, across the 6 groups (N = 11,739). The p-values are Holm-adjusted for the 27 answers tested; 27 of them differ by employment status at the 0.05 level. 6 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 employment status: the test of each answer, selected against not selected, by employment status
AnswerSelectedχ² (df = 5)Adjusted pCramér's V
Claude Code68.4%198.06< .0010.130
GitHub Copilot61.3%40.39< .0010.059
OpenAI Codex30.8%51.08< .0010.066
Cursor26.6%41.97< .0010.060
Google Antigravity16.7%142.66< .0010.110
Gemini Code Assist15.2%212.12< .0010.134
Open Code14.2%45.67< .0010.062
JetBrains AI13.4%14.32.0140.035
Windsurf6.8%49.09< .0010.065
Warp5.5%38.49< .0010.057
Cline4.7%21.43.0010.043
Pi4.6%35.94< .0010.055
Amazon Q Developer4.1%27.80< .0010.049
Continue4.0%34.26< .0010.054
Mistral Vibe3.3%53.46< .0010.067
Kilo Code3.3%56.19< .0010.069
Devin3.1%47.42< .0010.064
Google Jules2.6%178.79< .0010.123
Replit Agent2.4%139.93< .0010.109
Tabnine2.2%63.13< .0010.073
Aider2.2%52.26< .0010.067
Codium (Qodo)1.8%105.16< .0010.095
BLACKBOX AI1.7%234.17< .0010.141
Supermaven1.3%101.44< .0010.093
Trae1.3%142.08< .0010.110

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 27 answers gives 27 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 employment status. Cramér's V of 0.141 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 employment status

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 Employment. 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