gemini-4POST
Google staff question Gemini 4 on coding and real-world tasks despite strong benchmarks
A report says Google employees are raising concerns about Gemini 4's performance in coding and other key tasks, and that the model does less well on real-world work despite strong benchmark results.
First Squawk
@FirstSquawkArchived 28 days agoOriginally posted 2026.10.01
First Squawk @FirstSquawkOriginally posted 2026.10.01
GOOGLE IS GRAPPLING WITH INTERNAL SKEPTICISM OVER GEMINI 4 PERFORMANCE, WITH EMPLOYEES RAISING CONCERNS ABOUT THE MODEL'S PERFORMANCE IN CODING AND OTHER KEY TASKS DESPITE STRONG BENCHMARK RESULTS, AND GEMINI 4 REPORTEDLY PERFORMING LESS WELL WHEN PUT TO WORK ON REAL-WORLD TASKS.
x.com/firstsquawk/status/2105387845930324058Archived 2026.10.01 10:02