deepseek-v4.1IMAGE

DeepSeek V4.1 Flash vs GPT-6.1 Sol, Gemini 4 Argon and Opus 5.5 on one pelican prompt

The same pelican-on-a-bicycle prompt is run through DeepSeek V4.1 Flash 1017, GPT-6.1 Sol, Gemini 4 Argon and Claude Opus 5.5, with the author saying the new model's details keep up.

洋仔实验室

@yang3izcArchived 6 days agoOriginally posted 2026.10.22

DeepSeek V4.1 Flash vs GPT-6.1 Sol, Gemini 4 Argon and Opus 5.5 on one pelican prompt

洋仔实验室 @yang3izcOriginally posted 2026.10.22

Open original on X

四个模型画同一只骑车鹈鹕，差距真不小。同一句提示词、文件没改，摆一起对比： 1、DeepSeek V4.1 Flash 1017（max） 2、GPT-6.1 Sol（xhigh） 3、Gemini 4 Argon（high） 4、Claude Opus 5.5（max）我原以为新模型会输一截，结果细节没掉队。你们觉得哪张最像？

x.com/yang3izc/status/2112982368135114835Archived 2026.10.22 12:01