# OpenAI asks image-input workflows to rerun evals after an image-encoding fix

OpenAI Developers recommends rerunning evaluations and retrying workflows that use image inputs. Its changelog describes the fix as a bug in image encoding, following the image-understanding fix for GPT-6 Sol and GPT-6 Luna.

Language: en
Time zone: America/Los_Angeles
Current time (UTC, cached as of): 2026-11-17T15:12:00.000Z
Query date (America/Los_Angeles): 2026-11-17

HTML: https://didcodexreset.com/news/adae5d94132543dfb6eb54e3.html

Content language: en
Localization state: sameLanguage

Source: OpenAI Developers · Published 9/27/2026, 10:01:04

OpenAI Developers recommends that workflows using image inputs rerun their evaluations and be tried again. The [changelog](https://developers.openai.com/api/docs/changelog#:~:text=Fixed%20a%20bug%20in%20image%20encoding) describes the fix as a bug in image encoding.

The recommendation follows OpenAI Developers’ statement that a bug degrading image understanding in GPT-6 Sol and GPT-6 Luna has been fixed, with better results expected on visual tasks in the API and Codex, including computer use.

Tags: OpenAI, GPT-6, Image encoding, Evals

[View original post](https://x.com/OpenAIDevs/status/2104252318510420396)
