Codex vs Gemini vs Claude: Same Prompt, Wildly Different Results

thisiskp_ · x · 2026-08-25

A developer building in public gave OpenAI Codex, OpenCode, Gemini, and Claude the exact same one-line prompt and found the results were wildly different. He created a video showing the comparison of how each model handled the identical instruction.

Original post →

More from Models

Models channel →