Skip to content
Open navigation
OpenOpen workspace

Stack Overflow Developer Survey 2026

AI coding agents: Used in the past year by attitude toward ai

In the Very favorable group, 41% selected “OpenAI Codex”; in the Somewhat unfavorable group, 21% did. Of the 27 answers tested, “OpenAI Codex” differs most by attitude toward ai, a small association: χ²(5, N = 11013) = 285.71, Holm-adjusted p < .001, V = .16. 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: Used in the past year by attitude toward ai: percentage of each group's respondents who selected each answer, and respondent counts
AI coding agents: Used in the past yearVery favorable (A)Somewhat favorable (B)Neutral (C)Somewhat unfavorable (D)Very unfavorable (E)Not sure (F)All
Claude Code76.7%BCDEF2,86868.0%Dc2,30963.8%99263.4%95966.6%47062.9%6669.6%7,664
GitHub Copilot63.9%DE2,38864.1%DE2,17760.3%93758.2%88056.4%39860.0%6362.1%6,843
OpenAI Codex41.1%BCDE1,53530.6%CDE1,04126.4%D41021.2%32121.2%15031.4%3331.7%3,490
Cursor33.2%BCDE1,24027.1%Dc92223.3%36220.2%30623.8%16828.6%3027.5%3,028
Google Antigravity22.4%BCDE83916.4%DE55815.1%De23410.1%15310.6%7515.2%1617.0%1,875
Gemini Code Assist18.3%BDE68414.3%48715.7%e24412.4%18811.0%7817.1%1815.4%1,699
Open Code15.8%b58913.3%45314.4%22314.0%21212.9%9120.0%2114.4%1,589
JetBrains AI13.4%50213.9%47313.4%20913.0%19612.9%9112.4%1313.5%1,484
Windsurf8.6%BDE3216.4%2167.3%1145.2%794.8%346.7%77.0%771
Warp7.0%DEc2635.5%1875.0%784.0%603.4%245.7%65.6%618
Cline5.6%d2094.9%1664.5%703.6%553.5%256.7%74.8%532
Pi4.9%1844.8%1634.6%714.0%613.4%247.6%84.6%511
Amazon Q Developer5.2%D1934.0%1373.7%582.8%433.1%223.8%44.1%457
Continue4.4%1654.1%1384.1%633.4%512.5%186.7%74.0%442
Kilo Code4.6%BD1722.8%963.4%532.2%332.4%176.7%d73.4%378
Mistral Vibe2.7%1013.5%1193.8%593.8%573.1%224.8%53.3%363
Devin3.7%1402.6%892.7%423.0%463.5%253.8%43.1%346
Google Jules3.6%BDE1362.2%762.6%e411.6%240.8%64.8%E52.6%288
Replit Agent3.1%D1162.3%792.4%381.5%231.4%105.7%DE62.5%272
Aider2.5%952.1%721.9%291.8%272.0%145.7%d62.2%243
Tabnine2.5%952.0%672.0%311.7%262.4%173.8%42.2%240
Codium (Qodo)2.2%b841.4%461.8%281.5%231.3%92.9%31.8%193
BLACKBOX AI1.7%651.4%472.6%Be411.3%200.8%63.8%41.7%183
Supermaven1.4%521.3%431.2%191.2%181.1%84.8%BCDae51.3%145
Trae1.9%B720.9%301.2%190.9%140.6%44.8%BCDE51.3%144
Respondents3,7383,3981,5541,51270610511,013

A letter beside a percentage names the columns it is significantly higher than (uppercase 95%, lowercase 90%; pairwise column tests, Bonferroni-corrected). 19,890 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 = 285.71

df = 5, Holm-adjusted p < .001

Effect size

Cramér's V = 0.161

a small association

The strongest answer, APA-style: χ²(5, N = 11013) = 285.71, Holm-adjusted p < .001, V = .16. Each answer is tested on its own, as the respondents who selected it against those who did not, across the 6 groups (N = 11,013). The p-values are Holm-adjusted for the 27 answers tested; 15 of them differ by attitude toward ai 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 attitude toward ai: the test of each answer, selected against not selected, by attitude toward ai
AnswerSelectedχ² (df = 5)Adjusted pCramér's V
Claude Code69.6%151.00< .0010.117
GitHub Copilot62.1%32.60< .0010.054
OpenAI Codex31.7%285.71< .0010.161
Cursor27.5%119.27< .0010.104
Google Antigravity17.0%154.63< .0010.118
Gemini Code Assist15.4%47.83< .0010.066
Open Code14.4%12.86.2480.034
JetBrains AI13.5%1.24.9410.011
Windsurf7.0%29.41< .0010.052
Warp5.6%29.65< .0010.052
Cline4.8%13.09.2480.034
Pi4.6%6.70.7330.025
Amazon Q Developer4.1%18.86.0290.041
Continue4.0%9.04.6350.029
Kilo Code3.4%31.87< .0010.054
Mistral Vibe3.3%7.66.7050.026
Devin3.1%9.08.6350.029
Google Jules2.6%34.09< .0010.056
Replit Agent2.5%20.02.0190.043
Aider2.2%10.29.5380.031
Tabnine2.2%6.22.7330.024
Codium (Qodo)1.8%10.62.5350.031
BLACKBOX AI1.7%17.70.0440.040
Supermaven1.3%10.29.5380.031
Trae1.3%30.34< .0010.052

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 “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 0.161 is in the small range, which is real but modest: knowing someone's group tells you only a little about their answer.

With 11,013 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 AICodeAgentHaveWorkedWith (AI coding agents: Used in the past year) 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