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.
More from Models
- Security Researcher Waits a Month for Claude Cyber Trusted Access Approval — nptacek · 2026-08-25
- Codex overage allowance slashed to ~1%; exploit value > disclosure bounty — nptacek · 2026-08-25
- Developer complains about Ox Alpha's slow inference: 127 mins for 10 min task — altryne · 2026-08-25
- a16z partner blown away by access to unreleased AI model — AccBalanced · 2026-08-25
- Chinese LLMs 4-5 Months Behind US; ECI 155 May Be Reliability Threshold — Jsevillamol · 2026-08-25
- Optimizing Minimax H3: Best Settings for Quality and Consistency — Lair98 · 2026-08-25