Study Finds Grok and GPT Exhibit Strong Partisan Bias in Elections

1 reports archived1 independent sourcesupdated 10/24/2026, 23:00:00

Synthesis & Latest Updates

1 Sources Cross-Validated

A study by Cornell researchers reveals that when forced to choose candidates via API, Grok 4.7 recommended Republicans in 92% of cases, while GPT-6.1 Sol favored Democrats in 97%. Although consumer apps refuse direct voting advice, the underlying models show less than 10% agreement across nearly 500 races, highlighting significant partisan bias risks in LLMs.

LATEST/A study by Cornell researchers reveals that when forced to choose candidates via API, Grok 4.7 recommended Republicans in 92% of cases, while GPT-6.1 Sol favored Democrats in 97%. Although consumer apps refuse direct voting advice, the underlying models show less than 10% agreement across nearly 500 races, highlighting significant partisan bias risks in LLMs.

Hourly heat curve

2 fully observed hours

Fewer than 3 fully observed hours; trend not plotted yet.

Coverage timeline

Total 1 reports · Latest first

TechCrunch AIT2Oct 24, 23:00·68 pts
Study Finds Grok and GPT Exhibit Strong Partisan Bias in Elections
- Grok 4.7 leaned Republican in 92% of forced-choice scenarios, while GPT-6.1 Sol favored Democrats in 97%
- The two models agreed on recommendations in less than 10% of nearly 500 races
- Consumer apps refuse voting advice, but API calls expose the models' inherent stances
View Related Reports & Analysis Original Source