Skip to content
Open navigation
OpenOpen workspace

Stack Overflow Developer Survey 2026

AI coding agents: Want to use in the next 6 months by attitude toward ai

In the Very favorable group, 35% selected “OpenAI Codex”; in the Somewhat unfavorable group, 18% did. Of the 33 answers tested, “OpenAI Codex” differs most by attitude toward ai, a small association: χ²(5, N = 7276) = 136.26, 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 attitude toward ai, 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 attitude toward ai: percentage of each group's respondents who selected each answer, and respondent counts
AI coding agents: Want to use in the next 6 monthsVery favorable (A)Somewhat favorable (B)Neutral (C)Somewhat unfavorable (D)Very unfavorable (E)Not sure (F)All
Claude Code70.6%BCDE1,83265.7%1,60163.7%64061.9%53959.8%17464.1%5066.5%4,836
GitHub Copilot30.8%80032.8%79831.8%32028.0%24425.8%7537.2%2931.1%2,266
OpenAI Codex35.4%BCDE91927.0%DE65824.2%D24317.8%15518.9%5533.3%De2628.3%2,056
Open Code19.3%50118.4%44918.2%18317.3%15121.0%6123.1%1818.7%1,363
Cursor21.5%BDc55918.2%D44317.2%17313.1%11417.2%5017.9%1418.6%1,353
Google Antigravity17.1%BCD44513.8%D33712.6%d1278.7%7612.4%3620.5%D1614.3%1,037
Gemini Code Assist12.1%D31311.0%26710.1%1028.3%727.2%2111.5%910.8%784
Pi11.3%29310.2%2489.8%988.2%7112.0%3511.5%910.4%754
JetBrains AI9.5%24610.3%25011.3%1149.6%8410.7%3111.5%910.1%734
Mistral Vibe7.0%1817.3%1787.4%746.3%557.9%237.7%67.1%517
Windsurf6.4%BD1674.5%1104.8%483.1%273.8%1110.3%D85.1%371
Warp5.2%D1344.4%1085.2%D522.5%224.1%129.0%D74.6%335
Devin5.6%Db1464.0%d974.7%D472.0%175.2%d157.7%D64.5%328
Amazon Q Developer5.5%D1424.0%984.6%D462.1%184.8%149.0%D74.5%325
Kilo Code5.4%D1393.9%D944.7%D471.7%154.1%125.1%44.3%311
Cline4.8%1243.9%954.0%402.6%234.5%136.4%54.1%300
Google Jules4.4%D1153.9%D955.1%D511.7%153.8%116.4%d54.0%292
Continue4.1%1063.5%854.0%402.4%213.1%96.4%53.7%266
Replit Agent4.3%D1112.9%703.3%331.4%124.1%d126.4%D53.3%243
Aider3.9%d1003.1%763.4%341.8%163.8%115.1%43.3%241
BLACKBOX AI3.4%d882.6%643.6%d361.5%133.8%116.4%D53.0%217
Codium (Qodo)3.5%D912.7%663.1%311.5%133.1%96.4%D53.0%215
Emdash3.6%D932.5%603.3%331.4%123.8%117.7%Db63.0%215
Supermaven3.0%792.7%653.1%311.7%154.5%137.7%D62.9%209
Augment Code3.3%862.4%592.9%291.6%143.8%115.1%42.8%203
Respondents2,5952,4361,005871291787,276

A letter beside a percentage names the columns it is significantly higher than (uppercase 95%, lowercase 90%; pairwise column tests, Bonferroni-corrected). 23,627 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 “OpenAI Codex”

χ² = 136.26

df = 5, Holm-adjusted p < .001

Effect size

Cramér's V = 0.137

a small association

The strongest answer, APA-style: χ²(5, N = 7276) = 136.26, 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 = 7,276). The p-values are Holm-adjusted for the 33 answers tested; 10 of them differ by attitude toward ai at the 0.05 level.

AI coding agents: Want to use in the next 6 months by attitude toward ai: the test of each answer, selected against not selected, by attitude toward ai
AnswerSelectedχ² (df = 5)Adjusted pCramér's V
Claude Code66.5%38.19< .0010.072
GitHub Copilot31.1%12.53.3670.041
OpenAI Codex28.3%136.26< .0010.137
Open Code18.7%3.921.0000.023
Cursor18.6%34.27< .0010.069
Google Antigravity14.3%45.42< .0010.079
Gemini Code Assist10.8%14.55.2370.045
Pi10.4%8.47.6610.034
JetBrains AI10.1%3.361.0000.021
Mistral Vibe7.1%1.471.0000.014
Windsurf5.1%24.04.0060.057
Warp4.6%14.87.2190.045
Devin4.5%24.51.0050.058
Amazon Q Developer4.5%22.85.0100.056
Kilo Code4.3%22.87.0100.056
Cline4.1%9.14.6220.035
Google Jules4.0%17.27.0880.049
Continue3.7%7.62.7140.032
Replit Agent3.3%21.94.0130.055
Aider3.3%9.59.6180.036
BLACKBOX AI3.0%14.30.2490.044
Codium (Qodo)3.0%13.09.3160.042
Emdash3.0%20.36.0260.053
Supermaven2.9%14.08.2570.044
Augment Code2.8%10.99.6180.039

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 “OpenAI Codex” 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 attitude toward ai. Cramér's V of 0.137 is in the small range, which is real but modest: knowing someone's group tells you only a little about their answer.

With 7,276 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 “OpenAI Codex” 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 attitude toward ai

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 AISentiment. 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