Skip to content
Open navigation
OpenOpen workspace

Stack Overflow Developer Survey 2026

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

In the Other, please specify group, 17% selected “Approxima”; in the Master's degree (M.A., M.S., M.Eng., MBA, etc.) group, 1% did. Of the 33 answers tested, “Approxima” differs most by education, a small association: χ²(7, N = 7640) = 132.29, 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 education, 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 education: percentage of each group's respondents who selected each answer, and respondent counts
AI coding agents: Want to use in the next 6 monthsPrimary/elementary school (A)Secondary school (e.g. American high school, German Realschule or Gymnasium, etc.) (B)Some college/university study without earning a degree (C)Associate degree (A.A., A.S., etc.) (D)Bachelor's degree (B.A., B.S., B.Eng., etc.) (E)Master's degree (M.A., M.S., M.Eng., MBA, etc.) (F)Professional degree (JD, MD, Ph.D, Ed.D, etc.) (G)Other, please specify (H)All
Claude Code44.8%4355.5%25862.6%A59367.7%Ab15767.9%ABc2,07869.6%ABC1,56563.2%A30164.9%a7466.3%5,069
GitHub Copilot32.3%3130.5%14230.0%28429.7%6931.5%96531.0%69734.2%16342.1%4831.4%2,399
OpenAI Codex34.4%3328.6%13326.6%25225.4%5929.5%90227.1%61026.3%12531.6%3628.1%2,150
Open Code24.0%2324.3%EF11321.4%20322.8%5317.8%54417.1%38517.6%8425.4%2918.8%1,434
Cursor21.9%2118.9%8818.0%17119.8%4620.5%FG62717.0%38213.4%6429.8%FGc3418.8%1,433
Google Antigravity24.0%F2316.1%7515.3%14513.8%3215.4%F47112.0%26913.4%6426.3%EFGc3014.5%1,109
Gemini Code Assist13.5%1313.8%6412.9%12213.8%3210.0%30510.1%22613.2%6327.2%BCEFGd3111.2%856
Pi15.6%1512.5%5812.7%1209.9%2310.0%3059.3%21011.8%5621.9%EFd2510.6%812
JetBrains AI14.6%1411.2%5212.7%12012.1%289.8%2999.6%2158.4%4018.4%Gef2110.3%789
Mistral Vibe16.7%EF168.6%408.5%816.5%156.0%1857.0%1589.0%4318.4%CDEFb217.3%559
Windsurf11.5%FG117.5%F355.3%507.3%175.8%F1793.6%823.4%1617.5%BCEFG205.4%410
Warp13.5%EFG136.0%f286.9%F655.6%134.6%1403.1%703.8%1818.4%BCDEFG214.8%368
Devin12.5%EFG127.3%F346.3%F605.6%134.8%F1472.7%603.2%1521.1%BCDEFG244.8%365
Amazon Q Developer16.7%BCEFG166.0%F286.5%F626.9%F164.4%1342.8%643.8%1821.1%BCDEFG244.7%362
Kilo Code12.5%EFG124.9%235.7%F545.2%124.4%1363.2%713.4%1615.8%BCDEFG184.5%342
Google Jules13.5%EFdg136.9%Fe326.3%EF604.3%103.9%1192.6%585.0%2417.5%BCDEFG204.4%336
Cline11.5%EF115.4%255.6%F536.0%144.0%1212.8%644.6%2218.4%BCDEFG214.3%331
Continue13.5%CDEFG135.8%F275.2%F493.9%94.0%F1212.0%464.0%1916.7%BCDEFG194.0%303
Replit Agent7.3%F74.5%f215.0%F474.7%113.6%f1092.1%482.3%1116.7%BCDEFG193.6%273
Aider9.4%Fe94.1%195.0%F474.7%113.4%f1042.0%463.6%1715.8%BCDEFG183.5%271
Emdash11.5%EFG115.2%F245.2%Fe494.7%F113.1%F961.4%312.3%1116.7%BCDEFG193.3%252
BLACKBOX AI12.5%BCEFGd124.3%F204.5%F433.4%83.3%F1001.6%352.7%1316.7%BCDEFG193.3%250
Codium (Qodo)8.3%F84.3%F204.7%F453.0%73.4%F1051.5%332.5%1214.9%BCDEFG173.2%247
Supermaven8.3%F84.3%F204.9%F465.2%F123.0%F931.5%332.5%1212.3%BCEFG143.1%238
Augment Code9.4%EFg94.7%F224.4%F423.9%F93.0%F911.2%272.7%1316.7%BCDEFG193.0%232
Approxima10.4%EFGd104.1%F194.3%F412.6%62.7%F821.2%282.1%1016.7%BCDEFG192.8%215
Respondents964659482323,0612,2484761147,640

A letter beside a percentage names the columns it is significantly higher than (uppercase 95%, lowercase 90%; pairwise column tests, Bonferroni-corrected). 23,263 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 26 of the 33 answers: the most selected, and “Approxima”, the one that differs most. The CSV and JSON downloads have every answer.

Analysis

Results

Chi-square test of “Approxima”

χ² = 132.29

df = 7, Holm-adjusted p < .001

Effect size

Cramér's V = 0.132

a small association

The strongest answer, APA-style: χ²(7, N = 7640) = 132.29, 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 = 7,640). The p-values are Holm-adjusted for the 33 answers tested; 31 of them differ by education at the 0.05 level.

AI coding agents: Want to use in the next 6 months by education: the test of each answer, selected against not selected, by education
AnswerSelectedχ² (df = 7)Adjusted pCramér's V
Claude Code66.3%67.04< .0010.094
GitHub Copilot31.4%9.44.4450.035
OpenAI Codex28.1%9.16.4450.035
Open Code18.8%27.60.0010.060
Cursor18.8%29.67< .0010.062
Google Antigravity14.5%35.32< .0010.068
Gemini Code Assist11.2%46.78< .0010.078
Pi10.6%29.74< .0010.062
JetBrains AI10.3%20.98.0110.052
Mistral Vibe7.3%46.25< .0010.078
Windsurf5.4%64.59< .0010.092
Warp4.8%88.07< .0010.107
Devin4.8%115.63< .0010.123
Amazon Q Developer4.7%128.06< .0010.129
Kilo Code4.5%62.90< .0010.091
Google Jules4.4%101.22< .0010.115
Cline4.3%85.95< .0010.106
Continue4.0%100.89< .0010.115
Replit Agent3.6%83.66< .0010.105
Aider3.5%81.35< .0010.103
Emdash3.3%128.56< .0010.130
BLACKBOX AI3.3%118.14< .0010.124
Codium (Qodo)3.2%89.90< .0010.108
Supermaven3.1%76.12< .0010.100
Augment Code3.0%122.29< .0010.127
Approxima2.8%132.29< .0010.132

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 “Approxima” 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 education. Cramér's V of 0.132 is in the small range, which is real but modest: knowing someone's group tells you only a little about their answer.

With 7,640 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 “Approxima” 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 education

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 Education. 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