deepseek-v4.1IMAGE
Test claims only V4.1 Flash and Qwen 3.8 Max solved a task GPT-5.6 Sol failed
A user pushes back on comparing an older V4.1 Flash with GPT-5.6 Sol, saying in their own test only V4.1 Flash and Qwen 3.8 Max solved the problem.
泳往无前
@liurunArchived 11 days agoOriginally posted 2026.10.17
泳往无前 @liurunOriginally posted 2026.10.17
搞笑 了，这么多人那deepseek V4.1 flash（不是今天的版本） 和GPT5.6 Sol比较，他俩不是一个level,我实测的，附图这个题，只有deepseek 4.1 flash 和Qwen 3.8 max做的出来，其他模型都不行。
x.com/liurun/status/2111469903828201984Archived 2026.10.18 16:47