gpt-6VIDEO
Test shows GPT-6.1 Sol struggles to build the Eiffel Tower in Three.js
The author says Sol performs clearly worse than Astra and even Kimi on Three.js 3D scenes, and the token savings OpenAI claims did not show up.
Bhavy☄️
@Bhavani_00007Archived 2026.09.30Originally posted 2026.09.30
Bhavy☄️ @Bhavani_00007Originally posted 2026.09.30
GPT-6.1 Sol isn’t that good I asked it to build the Eiffel Tower in Three.js, and this is what it came up with. It performs pretty well on some other tests, but it failed badly on this scene compared to other models. For me, it still feels below Astra and even Kimi in frontend and 3D. OpenAI says it’s more efficient, but it seems to consume a lot of tokens.
x.com/bhavani_00007/status/2105035991425917335Archived 2026.09.30 10:15