gpt-6IMAGE
GPT-6 Sol underperforms GPT-5.6 Sol on DeepSWE, user says
weswinder shares comparison screenshots showing GPT-6 Sol scoring worse than GPT-5.6 Sol on DeepSWE, and suspects the benchmark is being downplayed.
Wes Winder
@weswinderArchived 2026.09.23Originally posted 2026.09.23

Wes Winder @weswinderOriginally posted 2026.09.23
gpt-6 sol is worse than gpt-5.6 sol on deepswe i get that it's cheaper but it's really weird having a new model that isn't better than the old model on every metric seems like they are trying to bury this benchmark
This post quotes another post: “OpenAI releases GPT-6 Sol and Luna with 50% lower API prices”
x.com/weswinder/status/2102475647562195050Archived 2026.09.23 10:20